© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2594
    Prev
    Next
    INDEX
    Explanations

    like rejection or interaction

    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_40_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
    瘤
    0.40
     arrêté
    0.39
     Isto
    0.39
     défendre
    0.39
    শেখ
    0.39
    ゐ
    0.39
    ẹt
    0.38
     hierarchical
    0.38
     TAB
    0.38
     отношениях
    0.38
    POSITIVE LOGITS
    狽
    0.40
     ثلاثه
    0.39
    柔
    0.38
     sheep
    0.37
     comparte
    0.37
     composure
    0.36
     कम्
    0.36
    勤務
    0.34
     conduc
    0.34
     obscurity
    0.34
    Activations Density 0.000%

    No Known Activations