© 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. 64938
    Prev
    Next
    INDEX
    Explanations

    testing before

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

    special occasions, standard values, code definitions

    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
    &+
    0.52
     '+
    0.47
    р
    0.46
    ⠈
    0.46
    ol
    0.45
    іл
    0.45
    ер
    0.44
    রত
    0.44
    ње
    0.44
    вец
    0.44
    POSITIVE LOGITS
    手法
    0.55
     Sauv
    0.49
     Bellevue
    0.48
     партия
    0.46
     colleagues
    0.46
    ms
    0.45
     presiding
    0.45
     لدى
    0.45
     сем
    0.45
    ❋
    0.45
    Activations Density 0.000%

    No Known Activations