© 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. 102580
    Prev
    Next
    INDEX
    Explanations

    snaps your

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

    connects to recruiters

    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
    ванные
    0.47
    ड़ियां
    0.45
    与其
    0.45
    蝟
    0.44
    räger
    0.43
    ículos
    0.43
    ியாக
    0.43
    unicorn
    0.43
    prevent
    0.42
     бүт
    0.42
    POSITIVE LOGITS
     switched
    0.43
     RO
    0.40
     Roe
    0.40
     P
    0.38
     switching
    0.38
     Kirch
    0.38
     COUN
    0.38
     Turnier
    0.38
     PAOK
    0.37
     Flughafen
    0.37
    Activations Density 0.001%

    No Known Activations