© 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. 117733
    Prev
    Next
    INDEX
    Explanations

    instance types

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

    The neuron is specialized in spotting numeric or alphanumeric scientific identifiers (e.g. mutation positions, charge states, polymorphism codes).

    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
    ire
    -1.02
    ‐
    -0.99
     R
    -0.96
    ere
    -0.94
    /*!
    -0.94
    INAS
    -0.93
     bizarre
    -0.93
    ERING
    -0.91
     nisi
    -0.90
     e
    -0.90
    POSITIVE LOGITS
    詣
    1.13
     cará
    1.11
    asties
    1.09
     type
    1.06
     oraz
    1.04
     and
    1.02
    dengan
    1.01
    ’，
    0.99
    <bos>
    0.99
     என்ற
    0.98
    Activations Density 0.243%

    No Known Activations