© 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-65K
    7. 65135
    Prev
    Next
    INDEX
    Explanations

    write lyrics, stories, or rephrased text

    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_65k_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
     टेंशन
    0.52
    緊張
    0.52
    நாயகம்
    0.52
     clickView
    0.49
    積極的に
    0.49
    紧张
    0.48
    ᓕ
    0.46
    ینګ
    0.45
    <unused54>
    0.45
     উদ্বেগ
    0.45
    POSITIVE LOGITS
     ARC
    0.48
     Marquez
    0.47
    akad
    0.45
     broken
    0.43
     initial
    0.42
     awarded
    0.41
     طا
    0.40
     labeled
    0.40
     scars
    0.40
     sunset
    0.39
    Activations Density 0.100%

    No Known Activations