© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57868
    Prev
    Next
    INDEX
    Explanations

    question, query, section, or item

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

    The neuron is strongly activated by numeric tokens, i.e. sequences of digits representing 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_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
     that
    -1.14
     this
    -1.13
     what
    -1.10
     from
    -1.08
    bigr
    -1.05
     after
    -1.02
     used
    -1.00
     how
    -0.98
    دام
    -0.98
    Some
    -0.95
    POSITIVE LOGITS
     amazingly
    1.08
     insanely
    1.05
     ALREADY
    1.05
     magnific
    1.02
     elegantly
    0.98
     strikingly
    0.96
     AMAZING
    0.96
     rám
    0.93
     pn
    0.91
     adorned
    0.91
    Activations Density 0.000%

    No Known Activations