© 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. 218807
    Prev
    Next
    INDEX
    Explanations

    read labels

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

    importance and potential

    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
    ạy
    0.54
     가능하다
    0.52
    Heather
    0.51
    Manisha
    0.49
     माध
    0.48
    呓
    0.47
     философ
    0.46
    CONFLICT
    0.46
    ান্তে
    0.46
    сий
    0.46
    POSITIVE LOGITS
     accumulated
    0.46
     tambour
    0.46
     the
    0.43
     commemoration
    0.43
     Mr
    0.43
     premiered
    0.41
     messing
    0.41
     cre
    0.41
    ؛
    0.41
    ».
    0.40
    Activations Density 0.000%

    No Known Activations