© 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. 41139
    Prev
    Next
    INDEX
    Explanations

    lists or structured text elements

    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
     มาก
    0.46
     マルチ
    0.45
     suatu
    0.44
    ေး
    0.43
    ppermint
    0.42
    하여
    0.42
    訕
    0.42
     iam
    0.42
     cheer
    0.42
    riso
    0.42
    POSITIVE LOGITS
     állapot
    0.48
     যখন
    0.45
    气质
    0.44
    Clk
    0.43
    வந்த
    0.43
     già
    0.42
     grau
    0.41
     Attitudes
    0.41
    犮
    0.41
    Grade
    0.41
    Activations Density 0.000%

    No Known Activations