© 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. 170230
    Prev
    Next
    INDEX
    Explanations

    hardware upgrade, replacement, or repair

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

    adaptation and caution

    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
    กอง
    0.48
     Tp
    0.48
    ICP
    0.47
    И
    0.47
    сайт
    0.47
    政府
    0.47
    }|\
    0.46
    太平
    0.45
    촤
    0.45
    h
    0.45
    POSITIVE LOGITS
     لكن
    0.54
     लेकिन
    0.53
    taxes
    0.48
    ন্ধে
    0.44
     بچ
    0.43
    യിലേ
    0.43
     حتی
    0.43
     thậm
    0.42
     مانند
    0.42
     exclusivement
    0.41
    Activations Density 0.000%

    No Known Activations