© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76535
    Prev
    Next
    INDEX
    Explanations

    throughout the season

    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
     fabricación
    0.45
    бо
    0.45
    barth
    0.43
    aurais
    0.43
    قر
    0.43
    Ꮻ
    0.43
    при
    0.42
    ⵄ
    0.42
    珉
    0.42
    </i>
    0.42
    POSITIVE LOGITS
     levels
    0.46
     fortiter
    0.44
     hor
    0.43
     την
    0.43
     tuan
    0.43
     أعلى
    0.42
     ye
    0.42
     ه
    0.42
     סי
    0.42
     Dương
    0.42
    Activations Density 0.001%

    No Known Activations