© 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. 197871
    Prev
    Next
    INDEX
    Explanations

    loans available, week seems, implementation into

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

    roles and contracts

    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
     "
    0.46
     wondered
    0.44
    にて
    0.44
     markedly
    0.43
     detected
    0.42
     👀
    0.41
     <
    0.40
     ("
    0.39
     COD
    0.39
     zoo
    0.38
    POSITIVE LOGITS
    alty
    0.47
    amless
    0.47
    bez
    0.46
    ress
    0.45
    ruktur
    0.44
    ukan
    0.44
    River
    0.44
    river
    0.43
    Sebagai
    0.43
    Без
    0.43
    Activations Density 0.001%

    No Known Activations