© 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. 59669
    Prev
    Next
    INDEX
    Explanations

    disability issues

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

    if you'd like

    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
    VE
    0.48
    ν
    0.47
     আন্দোলনে
    0.45
    sé
    0.40
    ಿಯ
    0.39
    μβ
    0.38
     பண்ண
    0.38
    hit
    0.38
     се
    0.38
     хочется
    0.37
    POSITIVE LOGITS
     interoper
    0.42
     karakteristik
    0.42
     stylesheet
    0.42
     retaliation
    0.42
     staffing
    0.41
     型
    0.41
    Accordingly
    0.41
     तैनात
    0.40
     comparator
    0.40
     exoskeleton
    0.40
    Activations Density 0.000%

    No Known Activations