© 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. 127240
    Prev
    Next
    INDEX
    Explanations

    new thirty, group, hell

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

    technical or formatting patterns

    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
    <0xA5>
    0.49
    ACING
    0.47
    umann
    0.47
    D
    0.46
    ún
    0.46
    ตาม
    0.45
    ЕНИ
    0.45
    ération
    0.45
    inson
    0.44
    uman
    0.44
    POSITIVE LOGITS
     ओनली
    0.49
     Petrol
    0.47
    protobuf
    0.46
    서
    0.46
     व्याप
    0.45
     त्रा
    0.45
     LMFBR
    0.43
     OKC
    0.43
     LSR
    0.43
     tensorflow
    0.42
    Activations Density 0.000%

    No Known Activations