© 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. 87931
    Prev
    Next
    INDEX
    Explanations

    text and language variety

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

    dividing by decimal

    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
     Dota
    0.45
     Assume
    0.41
     ->
    0.41
     relatifs
    0.40
     ISBN
    0.40
     Перед
    0.40
    bys
    0.40
    isal
    0.40
     trivially
    0.40
     indicates
    0.39
    POSITIVE LOGITS
     చేస్తున్న
    0.55
    ীরে
    0.52
    ENERGY
    0.49
    बीच
    0.47
    MECHAN
    0.46
     сказать
    0.46
    Qaeda
    0.45
     ହ
    0.45
     години
    0.44
    bestand
    0.44
    Activations Density 0.000%

    No Known Activations