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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27474
    Prev
    Next
    INDEX
    Explanations

    code snippets and symbols like `</`

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

    The neuron fires on tokens that are numeric sequences (integer constants or line‐number 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_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
     her
    -1.13
     will
    -0.93
     seca
    -0.93
     like
    -0.89
    Ừ
    -0.88
    styleType
    -0.88
    Když
    -0.87
    ừ
    -0.86
     other
    -0.86
     more
    -0.84
    POSITIVE LOGITS
    ッキリ
    1.02
    antian
    0.99
    žo
    0.97
    owaniem
    0.96
     sejumlah
    0.96
     modernisation
    0.96
    Lø
    0.95
    ené
    0.93
    Mvh
    0.93
     alp
    0.93
    Activations Density 0.001%

    No Known Activations