© 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. 161579
    Prev
    Next
    INDEX
    Explanations

    mile to island

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

    budget and allocation

    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
     JsonSerializer
    0.50
     zin
    0.48
    ın
    0.47
     cả
    0.47
    며
    0.47
    ㅈ
    0.47
     Mechanical
    0.47
     EGFR
    0.47
    리는
    0.46
     eutectic
    0.46
    POSITIVE LOGITS
     flowed
    0.46
    hadas
    0.45
    .’
    0.43
     voyez
    0.43
    َس
    0.43
    usky
    0.42
    noi
    0.42
     sombras
    0.41
    pays
    0.41
     Stras
    0.41
    Activations Density 0.000%

    No Known Activations