© 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. 245578
    Prev
    Next
    INDEX
    Explanations

    garage doors

    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
     curse
    0.47
    ?
    0.46
    ci
    0.45
    ）
    0.45
     элемента
    0.43
    folio
    0.41
     chunk
    0.41
     Station
    0.40
    uctive
    0.40
     There
    0.40
    POSITIVE LOGITS
    ات
    0.49
    ARE
    0.48
    क्के
    0.48
    PERSON
    0.48
    AKES
    0.47
    ياز
    0.47
    堯
    0.46
    Università
    0.46
    AST
    0.45
     keyboards
    0.45
    Activations Density 0.001%

    No Known Activations