© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 19484
    Prev
    Next
    INDEX
    Explanations

    names and sensitive content

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

    admitting mistake, resting, segmentation, approximation

    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
    름
    0.44
     oldCount
    0.43
    굵
    0.43
    дона
    0.43
    BACKGROUND
    0.42
     THINK
    0.41
    ROUND
    0.41
    Background
    0.40
    봇
    0.40
    istasis
    0.39
    POSITIVE LOGITS
     Kov
    0.46
     Fontaine
    0.46
     صلاح
    0.46
    porn
    0.46
     लीला
    0.46
     ပါ
    0.46
     Malam
    0.46
     proximity
    0.45
    nikov
    0.44
    ed
    0.44
    Activations Density 0.000%

    No Known Activations