© 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. 44341
    Prev
    Next
    INDEX
    Explanations

    punctation and common words

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

    list categories and descriptions

    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
     compromise
    0.50
    cri
    0.49
     expend
    0.48
     immobil
    0.47
     dinosaur
    0.46
    로
    0.46
    de
    0.45
    inas
    0.45
     humiliating
    0.44
     dysfunctional
    0.44
    POSITIVE LOGITS
    我们要
    0.46
    ائیگی
    0.46
    <unused42>
    0.46
    <unused27>
    0.45
     மொத்தம்
    0.45
     標準
    0.44
    敨
    0.44
    <unused82>
    0.43
    <unused43>
    0.43
     tầng
    0.42
    Activations Density 0.000%

    No Known Activations