© 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. 13548
    Prev
    Next
    INDEX
    Explanations

    unlocking potential and secrets

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

    unlocking potential and power

    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
    <0xA8>
    0.49
     обстоя
    0.46
     зим
    0.45
    єр
    0.45
    ั
    0.45
    ῆς
    0.45
    orted
    0.45
     рай
    0.44
    ถ่าย
    0.44
    ந்திய
    0.43
    POSITIVE LOGITS
     :
    0.44
     -
    0.43
     sz
    0.42
    Za
    0.41
    LIMIT
    0.41
     +,
    0.41
     sao
    0.40
     Instal
    0.39
    境界層
    0.39
     Klass
    0.39
    Activations Density 0.000%

    No Known Activations