© 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. 40505
    Prev
    Next
    INDEX
    Explanations

    legal rulings and personal statements

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

    wave crests

    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
    㴡
    0.50
     Blackpool
    0.48
    న్స్
    0.46
    멩
    0.46
    لها
    0.45
    冏
    0.45
     perspectiva
    0.44
    琿
    0.43
    하지
    0.43
    으며
    0.43
    POSITIVE LOGITS
     is
    0.55
     minutes
    0.49
    ä
    0.48
    连锁
    0.47
    il
    0.47
    awk
    0.47
    seconds
    0.46
    wa
    0.45
     बड़ी
    0.45
     wirelessly
    0.45
    Activations Density 0.000%

    No Known Activations