© 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. 64654
    Prev
    Next
    INDEX
    Explanations

    lights services

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

    rack setup

    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
    (
    0.45
     cypress
    0.42
     pathname
    0.42
     five
    0.41
     rapeseed
    0.41
     agent
    0.40
     leader
    0.40
     compact
    0.40
     SP
    0.40
     wint
    0.40
    POSITIVE LOGITS
    轵
    0.50
    襁
    0.50
    门口
    0.50
    Precision
    0.49
     খাবারের
    0.49
    鳝
    0.48
    читать
    0.48
    pleClass
    0.48
    Meals
    0.47
    Calories
    0.46
    Activations Density 0.000%

    No Known Activations