© 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. 101777
    Prev
    Next
    INDEX
    Explanations

    properties, pictures, ideas, price, home

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

    experiences vary

    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
    ellung
    0.51
     Valladolid
    0.49
    gateTime
    0.48
    gh
    0.48
     Yangzhou
    0.48
    KEYDOWN
    0.47
     घ
    0.46
    жд
    0.46
    gyro
    0.46
    mediately
    0.46
    POSITIVE LOGITS
    Option
    0.59
    Loader
    0.59
    Apex
    0.54
     Acquire
    0.53
    Justice
    0.52
    Emergency
    0.50
    Attorney
    0.50
    Home
    0.50
    Local
    0.50
    Offer
    0.49
    Activations Density 0.001%

    No Known Activations