© 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-262K
    7. 17809
    Prev
    Next
    INDEX
    Explanations

    Run the migrations

    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
     revenues
    0.46
     efficiencies
    0.38
     localStorage
    0.37
     visuals
    0.37
     dummies
    0.37
    ཌ
    0.37
     revenue
    0.36
     ENTRE
    0.36
     spirals
    0.36
     paraffin
    0.35
    POSITIVE LOGITS
    товых
    0.42
     τῶν
    0.39
     восем
    0.39
    गत
    0.39
     Governing
    0.38
    ξι
    0.38
     sorprend
    0.38
     ():
    0.38
     beş
    0.37
    தி
    0.37
    Activations Density 0.003%

    No Known Activations