© 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. 196608
    Prev
    Next
    INDEX
    Explanations

    American hero

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

    city or urban

    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
    festival
    0.49
     ->
    0.48
    coordinated
    0.47
    place
    0.47
    ://
    0.45
    rito
    0.45
    calories
    0.45
     Typically
    0.44
    use
    0.44
     বৈঠ
    0.44
    POSITIVE LOGITS
     σα
    0.52
     已
    0.50
     angegeben
    0.49
     ሃ
    0.49
     milliard
    0.48
    并没有
    0.46
     titul
    0.46
     نيك
    0.45
     그리스
    0.44
     chiffre
    0.44
    Activations Density 0.002%

    No Known Activations