© 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. 196661
    Prev
    Next
    INDEX
    Explanations

    power

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

    Uber Eats, tea, regression

    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
    В
    0.54
     ар
    0.50
    ić
    0.48
     Jij
    0.47
     belast
    0.47
     Vielzahl
    0.45
    Х
    0.45
     भिन्न
    0.44
     Schreib
    0.44
    략
    0.44
    POSITIVE LOGITS
    鵝
    0.46
    ALWAYS
    0.45
    ိုင်း
    0.44
    Edinburgh
    0.44
     radiolysis
    0.44
    烫
    0.43
     কানা
    0.43
    鹅
    0.42
     Value
    0.42
    ἲ
    0.42
    Activations Density 0.000%

    No Known Activations