© 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. 47843
    Prev
    Next
    INDEX
    Explanations

    maintained for

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

    factors influencing action

    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
    primir
    0.51
     पुष्टि
    0.51
    adinya
    0.48
    ром
    0.47
    وسی
    0.47
    ocot
    0.47
    ή
    0.47
    دید
    0.46
    エム
    0.46
    内容は
    0.46
    POSITIVE LOGITS
     regionale
    0.45
    predictor
    0.44
    晝
    0.43
     thats
    0.42
     spelt
    0.42
     sovereign
    0.41
     albeit
    0.39
     DEPEND
    0.39
     nacht
    0.39
    CATEGORY
    0.38
    Activations Density 0.000%

    No Known Activations