© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 56504
    Prev
    Next
    INDEX
    Explanations

    words indicating state followed by descriptor

    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
    ل
    0.50
    LY
    0.50
     dahil
    0.47
     коро
    0.46
    k
    0.46
    CELL
    0.46
     madd
    0.46
     var
    0.45
    ாக
    0.45
    )$.
    0.45
    POSITIVE LOGITS
    殑
    0.48
    ructive
    0.47
     recognising
    0.46
    徽
    0.45
    rimination
    0.43
    რულ
    0.41
    贵的
    0.41
     conspicuously
    0.41
     lengthened
    0.41
     Doe
    0.41
    Activations Density 0.006%

    No Known Activations