© 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. 221525
    Prev
    Next
    INDEX
    Explanations

    forest and soil

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

    minor tweaks to

    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
     انگیز
    0.50
     заниматься
    0.49
    禟
    0.48
    악
    0.45
    чными
    0.44
    看
    0.44
    יא
    0.44
     thanh
    0.43
     кей
    0.43
    கால
    0.43
    POSITIVE LOGITS
     perpendicular
    0.45
     (~
    0.45
     codon
    0.43
    amian
    0.43
     হয়েছে
    0.43
     (>
    0.42
    ensive
    0.42
     standardized
    0.41
     tacky
    0.41
    upper
    0.40
    Activations Density 0.001%

    No Known Activations