© 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. 173539
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    robustness and reliability

    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
     大
    0.57
     مك
    0.52
     Wad
    0.47
     風
    0.45
     fog
    0.44
     σχε
    0.44
     χ
    0.44
    .
    0.44
    まで
    0.44
     аба
    0.44
    POSITIVE LOGITS
    क्व
    0.59
    ahiye
    0.54
    ICENSE
    0.52
     realizzata
    0.48
     costituito
    0.47
    બ
    0.47
    kai
    0.47
     realizzato
    0.47
    썰
    0.47
     maniera
    0.46
    Activations Density 0.000%

    No Known Activations