© 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. 133285
    Prev
    Next
    INDEX
    Explanations

    firms focusing

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

    technical terms and specific contexts

    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
    ig
    0.59
    im
    0.52
    V
    0.52
    uc
    0.52
    ii
    0.52
     that
    0.51
    se
    0.50
    it
    0.50
    I
    0.50
    ir
    0.48
    POSITIVE LOGITS
    ونکو
    0.50
    흙
    0.50
    тех
    0.46
    техни
    0.46
     })_{
    0.45
     लिमिटेड
    0.45
    стема
    0.45
    戽
    0.45
     escrib
    0.44
     لي
    0.44
    Activations Density 0.001%

    No Known Activations