© 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. 101347
    Prev
    Next
    INDEX
    Explanations

    integral part

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

    home or house

    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
    н
    0.56
    ни
    0.49
    тному
    0.47
    르
    0.47
    ті
    0.47
     те
    0.47
    ρκ
    0.47
    decin
    0.46
    тись
    0.45
     matière
    0.45
    POSITIVE LOGITS
     EM
    0.46
    殤
    0.45
    ation
    0.45
     partid
    0.44
    。\
    0.44
    े
    0.44
     videom
    0.42
    朢
    0.42
    EM
    0.41
     datasource
    0.41
    Activations Density 0.000%

    No Known Activations