© 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. 6988
    Prev
    Next
    INDEX
    Explanations

    quantities and conditions

    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
    +
    0.44
     particularly
    0.42
     Ast
    0.41
    Ast
    0.40
     Rh
    0.40
    抽
    0.40
     more
    0.39
     Astor
    0.39
     all
    0.39
    Maple
    0.39
    POSITIVE LOGITS
     acceptez
    0.47
     yoj
    0.46
    𒊭
    0.46
     acept
    0.46
     fopen
    0.46
    ف
    0.46
    ത്തിന
    0.46
    به
    0.45
    锄
    0.45
    襬
    0.45
    Activations Density 0.003%

    No Known Activations