© 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. 190548
    Prev
    Next
    INDEX
    Explanations

    side, property, personal

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

    list of explanations

    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
    ك
    0.61
     واحدة
    0.57
    ד
    0.54
    ться
    0.50
    ف
    0.49
    ج
    0.47
     تھی
    0.47
    ר
    0.47
    ם
    0.46
    ع
    0.46
    POSITIVE LOGITS
    হেতু
    0.48
     znajdują
    0.46
    Energ
    0.45
    텔
    0.44
    ScriptObject
    0.42
     ettha
    0.42
    imagenes
    0.42
    chées
    0.41
    Record
    0.41
    of
    0.40
    Activations Density 0.001%

    No Known Activations