© 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. 40-GEMMASCOPE-2-RES-262K
    7. 133547
    Prev
    Next
    INDEX
    Explanations

    you

    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
    γκεκρι
    0.40
     ഭരണ
    0.39
     austerity
    0.39
     dispersive
    0.39
     Constit
    0.37
     satirical
    0.37
     warping
    0.36
    ="'$(
    0.35
     distributive
    0.35
     designing
    0.35
    POSITIVE LOGITS
    sponsor
    0.43
     Eldorado
    0.43
    )_{\
    0.42
     Kahn
    0.41
    rename
    0.40
    trends
    0.40
     Foss
    0.39
     Fossil
    0.38
     sponsor
    0.38
    సి
    0.38
    Activations Density 0.000%

    No Known Activations