© 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. 64293
    Prev
    Next
    INDEX
    Explanations

    names, marks, option

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

    gerunds and suffixes

    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
    のですが
    0.54
     Jahres
    0.49
     INTERACTIONS
    0.48
     réactions
    0.48
    旂
    0.48
    情的
    0.47
    你看
    0.46
    リーナ
    0.46
     déchets
    0.45
     MCSF
    0.45
    POSITIVE LOGITS
    is
    0.57
    en
    0.56
    in
    0.54
    ing
    0.54
    den
    0.54
    option
    0.54
    invoice
    0.51
    opens
    0.51
    m
    0.50
    y
    0.50
    Activations Density 0.000%

    No Known Activations