© 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. 55048
    Prev
    Next
    INDEX
    Explanations

    groups and populations

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

    lists followed by information

    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
    л
    0.48
    徕
    0.43
     последние
    0.41
     Office
    0.41
     morals
    0.41
     Town
    0.40
     পরিণত
    0.40
     tenacious
    0.40
     pudi
    0.40
     etab
    0.40
    POSITIVE LOGITS
     여름
    0.52
     為
    0.51
    中は
    0.48
     乀
    0.48
     掛
    0.47
    őr
    0.46
     冖
    0.45
    াড়
    0.45
     軽量
    0.45
    ಗ್ಗ
    0.44
    Activations Density 0.000%

    No Known Activations