© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110804
    Prev
    Next
    INDEX
    Explanations

    variable assignment or mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite

    the single lowercase letter 'l' used as a variable name in code or mathematical expressions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on the standalone lowercase letter “l” token (e.g. when used as a variable name or URL parameter).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     principais
    -1.41
     example
    -1.37
    },
    -1.34
    ↵
    -1.30
    ↵↵
    -1.28
    ^.
    -1.23
    </strong>
    -1.17
     праздника
    -1.16
    LETTER
    -1.16
     ideas
    -1.16
    POSITIVE LOGITS
     Jér
    1.25
     offensi
    1.23
    侥
    1.19
     extraordin
    1.17
     Zé
    1.17
     ENTR
    1.16
     amie
    1.16
     丈
    1.16
     skul
    1.13
    ismuth
    1.13
    Activations Density 0.114%

    No Known Activations