© 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. 2908
    Prev
    Next
    INDEX
    Explanations

    basic, biological, order, Yellow, structure

    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
    Cloud
    0.48
    incott
    0.45
    cloud
    0.43
    getPassword
    0.42
    Legacy
    0.42
     শান্তি
    0.40
    зре
    0.40
    跛
    0.40
    PLS
    0.39
    Tobacco
    0.39
    POSITIVE LOGITS
     professionally
    0.54
     contemporaneous
    0.54
     two
    0.52
     erreur
    0.52
    ਲ
    0.52
     formally
    0.51
     ulcer
    0.50
     unethical
    0.50
     kaks
    0.50
     repet
    0.49
    Activations Density 0.022%

    No Known Activations