© 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. 33844
    Prev
    Next
    INDEX
    Explanations

    constructor or initializer functions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     any
    -1.04
     different
    -1.00
     voetballer
    -0.96
     dificultades
    -0.95
    ứt
    -0.94
     each
    -0.94
    剽
    -0.91
    QPalette
    -0.90
     kı
    -0.90
     individually
    -0.90
    POSITIVE LOGITS
     dvd
    0.91
    Spinach
    0.91
     patienter
    0.88
    giques
    0.88
     لأنه
    0.88
     cómics
    0.87
    +$
    0.87
    而是
    0.87
     vitesses
    0.85
    ㅃ
    0.84
    Activations Density 0.003%

    No Known Activations