© 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. 201745
    Prev
    Next
    INDEX
    Explanations

    program, firms, community, protect

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

    estimates, variables, 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
     epistle
    0.52
     আক্রমণ
    0.48
    ूँ
    0.48
     Epistle
    0.47
    蕗
    0.47
    নিক
    0.46
    ALY
    0.46
    ిత
    0.45
     elektronic
    0.45
    ATH
    0.45
    POSITIVE LOGITS
    atge
    0.54
    ra
    0.52
    og
    0.50
    re
    0.49
    d
    0.49
    ag
    0.47
    at
    0.46
     साइंस
    0.45
    clar
    0.45
     surveyed
    0.45
    Activations Density 0.000%

    No Known Activations