© 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. 128642
    Prev
    Next
    INDEX
    Explanations

    your domain

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

    risk impact consequences

    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
    machine
    0.50
    irre
    0.45
    portable
    0.44
     الامتحان
    0.44
     طريقه
    0.44
     బ్యాంకు
    0.43
     pediat
    0.43
     ጡ
    0.42
     пен
    0.42
    рино
    0.42
    POSITIVE LOGITS
     dihad
    0.44
     wenn
    0.44
    就可以了
    0.43
     bevat
    0.42
     fehl
    0.42
     startDate
    0.42
     sebagai
    0.42
     commemor
    0.42
     berbagai
    0.42
     antwort
    0.42
    Activations Density 0.000%

    No Known Activations