© 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. 161729
    Prev
    Next
    INDEX
    Explanations

    listing courtesy

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

    Loom video

    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
     రీ
    0.52
     开始
    0.49
    osas
    0.49
    Por
    0.49
    Sun
    0.48
     élargies
    0.47
    }
    0.45
    فاض
    0.44
    的
    0.44
    LIMITED
    0.44
    POSITIVE LOGITS
     fortuit
    0.49
     mares
    0.46
    deki
    0.45
    isinde
    0.45
     unbear
    0.45
    レスレット
    0.45
     LES
    0.44
     jako
    0.44
    relse
    0.44
     kilometres
    0.44
    Activations Density 0.000%

    No Known Activations