© 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. 21685
    Prev
    Next
    INDEX
    Explanations

    oven, however

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

    calculating probabilities and combinations

    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
     안전
    0.47
    囯
    0.47
    rots
    0.46
     Сьогодні
    0.46
    安全
    0.45
    四个
    0.45
    㓡
    0.45
    rick
    0.45
    esri
    0.44
    രിക്കുന്നു
    0.42
    POSITIVE LOGITS
    ί
    0.44
     tendencies
    0.42
    mM
    0.42
     ஃப
    0.42
    kD
    0.42
    ה
    0.41
     solubilities
    0.40
    ся
    0.40
    மோ
    0.40
    ses
    0.39
    Activations Density 0.001%

    No Known Activations