© 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. 7213
    Prev
    Next
    INDEX
    Explanations

    progression with each

    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
    Replacement
    0.43
    变成
    0.42
    원
    0.40
     Replacement
    0.39
    纸
    0.39
    first
    0.39
    replacement
    0.38
    變成
    0.38
     seater
    0.38
    defining
    0.38
    POSITIVE LOGITS
    かもしれません
    0.42
     zároveň
    0.39
     Besuch
    0.38
    गर्भ
    0.38
    ższ
    0.38
    🥃
    0.37
    戮
    0.36
    ")}}'
    0.36
    cura
    0.35
    ש
    0.35
    Activations Density 0.000%

    No Known Activations