© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 69861
    Prev
    Next
    INDEX
    Explanations

    code identifiers and values

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

    The neuron fires on code-style identifiers made up of lowercase words and numbers joined by underscores (i.e. snake_case tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     również
    -1.27
     également
    -1.18
    Also
    -1.14
     also
    -1.08
    also
    -1.05
     também
    -1.02
     также
    -1.02
    And
    -0.98
    for
    -0.96
     arī
    -0.93
    POSITIVE LOGITS
    Mó
    1.17
     granito
    1.08
     seigneur
    1.07
    Komple
    1.06
    Kein
    1.05
     poulet
    1.05
     sés
    1.04
     menthe
    1.03
    <bos>
    1.02
     guitarra
    1.02
    Activations Density 0.323%

    No Known Activations