© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15268
    Prev
    Next
    INDEX
    Explanations

    the state or number

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

    rates, missing, original, father

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Teenage
    0.57
     Otherwise
    0.56
    isées
    0.54
    cé
    0.53
    Otherwise
    0.52
    There
    0.52
    nYou
    0.50
    텍
    0.49
    gew
    0.49
    cima
    0.49
    POSITIVE LOGITS
     bait
    0.48
     '^
    0.43
     sowing
    0.43
     equidistant
    0.42
     '*')
    0.42
    その
    0.42
     possession
    0.42
     paving
    0.42
     sunroof
    0.42
     extends
    0.41
    Activations Density 0.000%

    No Known Activations