© 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. 2926
    Prev
    Next
    INDEX
    Explanations

    MDF-DU, IT firm, RCA RCD, Chicago Tribune

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

    amygdalin or tortilla wraps

    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
    ència
    0.54
    ée
    0.54
    ong
    0.51
    ño
    0.50
    :
    0.46
     mins
    0.45
    ого
    0.44
    е
    0.44
    ко
    0.43
     factor
    0.43
    POSITIVE LOGITS
     enteral
    0.57
     choroby
    0.49
     ഭക്ഷണം
    0.48
    IZATION
    0.48
     ಅವು
    0.47
    螃
    0.46
    هایی
    0.46
     Itali
    0.46
    URNIZOR
    0.46
    SCHRAMM
    0.46
    Activations Density 0.000%

    No Known Activations