© 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. 27927
    Prev
    Next
    INDEX
    Explanations

    render without

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

    testing frameworks

    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
    ٦
    0.43
     فہرست
    0.43
    list
    0.41
    ন্থা
    0.40
     Lietuvos
    0.40
    రికీ
    0.40
    ヤマハ
    0.39
     путь
    0.39
    侶
    0.39
     шу
    0.39
    POSITIVE LOGITS
     fibrils
    0.51
     moldings
    0.48
     cells
    0.46
     izol
    0.46
     initiates
    0.45
     filaments
    0.45
     myocytes
    0.44
     assays
    0.42
     isolates
    0.42
     프
    0.41
    Activations Density 0.000%

    No Known Activations