© 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. 30576
    Prev
    Next
    INDEX
    Explanations

    essay titles and topics

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

    The neuron is selectively activating on multi‐digit numeric tokens (e.g. years, codes, counts, or other long 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
     mouseClicked
    -1.09
    -------
    -0.96
    챕
    -0.95
    ===========
    -0.94
     cultur
    -0.93
    ঙ্
    -0.93
    ᕙ
    -0.92
     twa
    -0.92
    ===============
    -0.91
    =========
    -0.91
    POSITIVE LOGITS
     Who
    1.28
     Where
    1.23
     what
    1.20
     What
    1.17
     How
    1.13
     Types
    1.10
     Is
    1.10
    ",
    1.09
     how
    1.08
    What
    1.07
    Activations Density 0.003%

    No Known Activations