© 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. 64742
    Prev
    Next
    INDEX
    Explanations

    age or amount

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

    warranty and politeness

    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
     строение
    0.47
     Atkins
    0.46
    chapters
    0.44
    >
    0.43
    UMNS
    0.42
    examin
    0.41
    imag
    0.41
    prs
    0.41
    lem
    0.41
    ambia
    0.41
    POSITIVE LOGITS
     écologique
    0.48
    釣
    0.46
    承诺
    0.46
     ισ
    0.45
     warranty
    0.44
    蟑
    0.44
     Garantie
    0.44
    ాలు
    0.44
     설치
    0.44
    經營
    0.43
    Activations Density 0.000%

    No Known Activations