© 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. 222816
    Prev
    Next
    INDEX
    Explanations

    stay right with

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

    edgy, game, start, rice

    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
    뗑
    0.53
     diagn
    0.49
    보는
    0.49
     Yachts
    0.48
    ेट
    0.48
    फोन
    0.47
    และการ
    0.47
    стройка
    0.46
    ข้าว
    0.46
     restor
    0.46
    POSITIVE LOGITS
    aligned
    0.51
    is
    0.48
    ಿಕ
    0.46
    5
    0.46
    <0x9E>
    0.46
    );
    0.45
    feather
    0.44
    ledge
    0.43
    ata
    0.43
    always
    0.43
    Activations Density 0.001%

    No Known Activations