© 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. 194441
    Prev
    Next
    INDEX
    Explanations

    states and actions

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

    mathematical and list formatting

    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
     ஸ்த
    0.50
    f
    0.49
    ből
    0.43
    ième
    0.42
    elv
    0.42
    滟
    0.42
    addAttribute
    0.41
    ೭
    0.41
    as
    0.41
    arabic
    0.41
    POSITIVE LOGITS
    確かに
    0.49
     ক্ষমতাসীন
    0.46
     Hokkaido
    0.43
     blockchain
    0.43
     শিক্ষার্থীরা
    0.43
     ছাত্রলীগের
    0.42
    佲
    0.41
     داستان
    0.41
    Caprio
    0.41
    緩
    0.40
    Activations Density 0.000%

    No Known Activations