© 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. 86275
    Prev
    Next
    INDEX
    Explanations

    foreign and technical terms

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

    even comparison

    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
    ל
    0.52
    imate
    0.50
     रक्षाबंधनाच्या
    0.48
     તપાસ
    0.47
    ower
    0.47
     Uso
    0.46
     papi
    0.46
     Kiev
    0.46
    uzzles
    0.46
    ȩ
    0.45
    POSITIVE LOGITS
     dissonance
    0.47
     needlessly
    0.47
    REDIRECT
    0.42
    RIBUTION
    0.42
    ヒト
    0.41
    ক্ষেত্র
    0.41
     unexpectedly
    0.41
    という意味
    0.41
     addirittura
    0.41
     рубе
    0.39
    Activations Density 0.000%

    No Known Activations