© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 110400
    Prev
    Next
    INDEX
    Explanations

    understanding, hidden, tablets, proteins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ᅨ
    0.48
     anex
    0.46
    шою
    0.46
     નિય
    0.45
     요구
    0.45
     vanadium
    0.43
    v
    0.43
     teş
    0.42
     ljud
    0.42
     determina
    0.42
    POSITIVE LOGITS
     Projection
    0.45
     நாளை
    0.44
    Personensuche
    0.42
     Christ
    0.42
    Projection
    0.42
     ज़रूरत
    0.42
    islang
    0.42
    igon
    0.41
    hutang
    0.41
    ><?
    0.41
    Activations Density 0.000%

    No Known Activations