© 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. 64630
    Prev
    Next
    INDEX
    Explanations

    describing tasks or subtasks

    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
    in
    0.65
    and
    0.57
    c
    0.55
     Can
    0.50
    s
    0.48
     As
    0.47
     as
    0.45
     Europe
    0.45
     The
    0.44
    ific
    0.44
    POSITIVE LOGITS
    Issledovatel
    0.56
    钎
    0.54
    Methylsulfanyl
    0.52
    ၻ
    0.50
    Benzoimidazol
    0.49
    larınız
    0.49
    锕
    0.49
     प्लेइंग
    0.48
    鳃
    0.48
    ⵕ
    0.47
    Activations Density 0.003%

    No Known Activations