© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11719
    Prev
    Next
    INDEX
    Explanations

    list markers or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    here Okay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     monstrous
    0.36
    朼
    0.36
     monotonous
    0.36
    宻
    0.36
    ್ರ
    0.35
    仼
    0.34
     wretched
    0.33
    Რ
    0.33
    閔
    0.33
    ्रो
    0.33
    POSITIVE LOGITS
     T
    0.37
     Science
    0.37
    T
    0.36
     Bazaar
    0.35
     Dave
    0.35
     Office
    0.35
     Jaw
    0.35
     Sands
    0.34
     Valley
    0.33
     Mike
    0.33
    Activations Density 0.050%

    No Known Activations