© 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. 11983
    Prev
    Next
    INDEX
    Explanations

    possessive names like Bernard's

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

    no hop, meaning, 3 questions

    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
    s
    0.79
    ের
    0.48
     frequent
    0.48
    idio
    0.44
    ográfico
    0.44
     addictive
    0.43
    ség
    0.43
    ی
    0.43
    ísima
    0.43
     sunday
    0.43
    POSITIVE LOGITS
    ברה
    0.52
    ניה
    0.50
    າດ
    0.49
    रिपोर्ट
    0.48
    ቃል
    0.48
    鈮
    0.46
    บาด
    0.46
    沩
    0.46
    Bernard
    0.46
    Longueur
    0.46
    Activations Density 0.000%

    No Known Activations