© 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. 30946
    Prev
    Next
    INDEX
    Explanations

    model labels and identifiers

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

    This neuron responds to technical labels and reporting terms—words used to denote that a value or field is being “reported” or identified (e.g. reporting thresholds, model 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
     cantar
    -0.77
     enlace
    -0.77
     responde
    -0.76
     phê
    -0.75
     verwenden
    -0.75
     eikä
    -0.74
     years
    -0.73
    发了
    -0.71
     antigu
    -0.71
     supera
    -0.69
    POSITIVE LOGITS
     static
    1.67
    static
    1.35
     pelatih
    0.92
    आर
    0.88
    ायर
    0.88
    Protos
    0.88
    ();*/
    0.86
    moveTo
    0.84
    ???:
    0.83
    😡
    0.82
    Activations Density 0.000%

    No Known Activations