© 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. 26351
    Prev
    Next
    INDEX
    Explanations

    is genuinely true

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

    exceptions and special cases

    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
    琿
    0.48
    Plugins
    0.47
    ServiceName
    0.46
     হবে
    0.46
     উঠলাম
    0.45
    伈
    0.45
    ২৬
    0.44
    崱
    0.43
    サービス
    0.43
    Quarter
    0.43
    POSITIVE LOGITS
     lact
    0.47
     arterioles
    0.47
     Coca
    0.47
     Alzheimer
    0.46
     Exceptions
    0.46
     spermato
    0.44
     vehement
    0.44
     alent
    0.43
     diuretics
    0.43
     Oktoberfest
    0.43
    Activations Density 0.000%

    No Known Activations