© 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. 14761
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and points

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

    ABC points in geometry

    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
    রাজনৈতিক
    0.45
    ⊠
    0.45
    <unused89>
    0.44
    叠加
    0.43
    樘
    0.43
    <unused98>
    0.42
    蚛
    0.42
    بيض
    0.41
    <unused95>
    0.41
    파트
    0.41
    POSITIVE LOGITS
     C
    0.57
     B
    0.50
     O
    0.46
     G
    0.46
    }
    0.44
    C
    0.43
     K
    0.43
     bracelet
    0.43
    B
    0.42
     J
    0.42
    Activations Density 0.001%

    No Known Activations