© 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. 237041
    Prev
    Next
    INDEX
    Explanations

    Resources, translations, manufacturer types

    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
    del
    0.53
    t
    0.51
    d
    0.51
    labor
    0.50
    erer
    0.50
    en
    0.49
    fort
    0.49
    delt
    0.49
    Labor
    0.48
    dell
    0.48
    POSITIVE LOGITS
    ัตว์
    0.46
    куда
    0.45
    শব
    0.44
    عادة
    0.43
    秅
    0.43
    もあり
    0.43
     частично
    0.43
     funcionan
    0.42
    أي
    0.42
     macromolecules
    0.42
    Activations Density 0.000%

    No Known Activations