© 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. 45141
    Prev
    Next
    INDEX
    Explanations

    over all

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

    why consent / authorization

    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
    🔧
    0.49
    Wanted
    0.48
    🚜
    0.48
    abila
    0.45
     chcete
    0.45
    👚
    0.45
     shavings
    0.44
    ⌵
    0.44
    🙉
    0.44
    𝜁
    0.44
    POSITIVE LOGITS
     непосред
    0.50
     Caed
    0.46
     mesmo
    0.45
     Verlag
    0.45
     Luxor
    0.45
     Metro
    0.44
     Paragon
    0.44
     Comte
    0.44
     Seward
    0.43
    amless
    0.43
    Activations Density 0.000%

    No Known Activations