© 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. 4796
    Prev
    Next
    INDEX
    Explanations

    retail

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

    chess notation, chess pieces, positions

    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
     stones
    0.45
     Inquiry
    0.44
     *(
    0.43
     Audit
    0.43
     Toner
    0.43
     rocks
    0.42
     Arsenal
    0.42
     audioEngine
    0.42
     s
    0.42
    низу
    0.42
    POSITIVE LOGITS
    recover
    0.50
     крупных
    0.50
    rael
    0.49
    encije
    0.49
    焔
    0.49
    webpack
    0.49
     круп
    0.47
     अफसर
    0.46
    businessman
    0.46
    rue
    0.46
    Activations Density 0.000%

    No Known Activations