© 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. 99473
    Prev
    Next
    INDEX
    Explanations

    naming, how, secretion

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

    distrust and fear

    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
    urls
    0.53
    isotope
    0.50
    marks
    0.50
    pixel
    0.49
    itation
    0.47
     머
    0.46
     erkl
    0.46
     heading
    0.46
     व्याख्या
    0.46
     Heading
    0.46
    POSITIVE LOGITS
     তাহলে
    0.50
     suf
    0.49
    πλ
    0.49
     μέ
    0.45
     refuer
    0.45
     pampered
    0.44
    اع
    0.43
     perme
    0.43
     υπο
    0.43
    ီ
    0.43
    Activations Density 0.000%

    No Known Activations