© 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. 22-GEMMASCOPE-RES-131K
    4. 54225
    Prev
    Next
    INDEX
    Explanations

    broad range of items

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

    The neuron activates on standalone numeric tokens (digits or numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     at
    -1.23
     sommige
    -1.20
     also
    -1.20
     or
    -1.14
     ještě
    -1.13
    ࿚
    -1.12
    Legături
    -1.11
     heerlijk
    -1.09
    astă
    -1.06
    蕎麦
    -1.06
    POSITIVE LOGITS
     everything
    1.42
     such
    1.39
     anything
    1.32
    各种
    1.29
     various
    1.29
     varied
    1.29
    various
    1.25
     всички
    1.25
     variety
    1.24
     include
    1.20
    Activations Density 0.035%

    No Known Activations