© 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. 145602
    Prev
    Next
    INDEX
    Explanations

    Groves, Minister, world

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

    affect, PWM, Output, Metadata

    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
    HAR
    0.52
    Рас
    0.49
    ΤΑ
    0.48
    ##
    0.46
    СТЬ
    0.46
    INF
    0.45
    гія
    0.45
    Defaults
    0.45
    DEVICE
    0.44
    അ
    0.44
    POSITIVE LOGITS
     Bilbao
    0.52
     tongue
    0.51
     cove
    0.48
     বলেছিলেন
    0.46
     isn
    0.44
     Zimbabwean
    0.44
     ribbed
    0.44
     Ugandan
    0.44
     Hond
    0.43
     Fibonacci
    0.43
    Activations Density 0.000%

    No Known Activations