© 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. 49798
    Prev
    Next
    INDEX
    Explanations

    following common grammatical structures

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

    describing abstract capabilities or qualities

    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
    Nine
    0.54
    p
    0.54
    千葉
    0.52
    NOR
    0.51
    Mother
    0.50
    G
    0.49
    Ret
    0.48
    JUNE
    0.48
    Changes
    0.47
    Ch
    0.47
    POSITIVE LOGITS
    ird
    0.47
     আচ
    0.47
     AppMethodBeat
    0.46
    楖
    0.46
     Vereinigten
    0.46
    panelMenuList
    0.45
     Vereinigte
    0.45
    printDialog
    0.44
    idade
    0.42
     gennem
    0.42
    Activations Density 0.000%

    No Known Activations