© 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. 22-GEMMASCOPE-RES-131K
    7. 15384
    Prev
    Next
    INDEX
    Explanations

    subscripts and superscripts

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

    This neuron is triggered by tokens that are part of chemical‐equation notation (e.g. the “EQU” marker and the numeric stoichiometric values).

    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
    igneur
    -1.12
     Nedir
    -1.04
    _{{\
    -1.02
     تانيه
    -1.02
    ParallelGroup
    -1.01
    おわりに
    -0.98
    фильм
    -0.95
    сете
    -0.95
    bory
    -0.94
    なら
    -0.93
    POSITIVE LOGITS
    diferentes
    1.10
     virtud
    1.02
    ous
    1.00
    修炼
    1.00
    ヨン
    0.99
    كما
    0.99
     Zaire
    0.97
    Distancia
    0.97
    initialise
    0.96
    ouse
    0.96
    Activations Density 0.004%

    No Known Activations