© 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. 5978
    Prev
    Next
    INDEX
    Explanations

    AI consultant

    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
     обычно
    0.49
     الموضوع
    0.49
     ફરિયા
    0.45
     معظم
    0.44
     পর
    0.43
     बाद
    0.42
     medida
    0.41
    〰
    0.41
    葡萄
    0.41
     baad
    0.40
    POSITIVE LOGITS
    uther
    0.52
    datast
    0.47
    診断
    0.46
     Merger
    0.46
    qualiter
    0.45
    ünstler
    0.44
    '.
    0.43
     sinist
    0.43
    र्गन
    0.42
    FrameID
    0.42
    Activations Density 0.011%

    No Known Activations