© 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. 130007
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on standalone numeric tokens (e.g. version or lesson numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    version or lesson number

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     المصرية
    -1.20
    lée
    -1.02
    原标题
    -0.97
     poda
    -0.97
    rimir
    -0.96
    èges
    -0.96
    >
    -0.95
     any
    -0.94
    三日
    -0.93
    AIRES
    -0.93
    POSITIVE LOGITS
    .
    1.23
    </b>
    1.08
     reiter
    1.05
     kolejny
    1.03
    ङ
    1.00
    -
    1.00
     szinte
    0.97
    un
    0.97
    0.96
     solteiro
    0.95
    Activations Density 0.000%
    No Known Activations