© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111409
    Prev
    Next
    INDEX
    Explanations

    master, hands, secretly insecure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ב
    0.57
     ל
    0.56
     כ
    0.56
     ח
    0.53
     excret
    0.51
     מ
    0.50
     ס
    0.50
     発
    0.50
     で
    0.49
     לא
    0.49
    POSITIVE LOGITS
    ът
    0.56
    ят
    0.52
    وست
    0.51
    و
    0.50
    وون
    0.47
    ötz
    0.47
    岘
    0.47
    其他
    0.46
    ώσεις
    0.46
    питы
    0.44
    Activations Density 0.000%

    No Known Activations