© 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. 105667
    Prev
    Next
    INDEX
    Explanations

    list, conclusion, email, bold, created

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

    categorize things, catalyze reactions, catalog search

    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
     wereld
    0.48
     část
    0.46
    Hak
    0.45
    饭
    0.45
    转移
    0.45
    Сан
    0.45
    登山
    0.44
    2
    0.44
    儿童
    0.43
    施設
    0.43
    POSITIVE LOGITS
    ata
    0.56
    ate
    0.54
    exa
    0.54
    ao
    0.52
     Affair
    0.52
    atk
    0.51
    avoid
    0.49
     Angriff
    0.48
    avip
    0.48
    gpg
    0.48
    Activations Density 0.000%

    No Known Activations