© 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-262K
    4. 42102
    Prev
    Next
    INDEX
    Explanations

    suggestions for adding or changing phrases

    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
    ort
    0.46
     virtually
    0.45
     European
    0.44
     in
    0.42
     efficient
    0.42
     Io
    0.41
     winter
    0.41
     I
    0.41
     well
    0.41
     never
    0.41
    POSITIVE LOGITS
     lysates
    0.52
     Pública
    0.51
    氿
    0.51
    RatingDiff
    0.48
    भाषित
    0.48
    कांग्रेस
    0.47
     بشأن
    0.47
    引号
    0.46
    ानंद
    0.46
    Semitism
    0.46
    Activations Density 0.009%

    No Known Activations