© 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. 115831
    Prev
    Next
    INDEX
    Explanations

    your consent

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

    non-english characters

    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
    実に
    0.46
    ’
    0.44
     Appalachian
    0.43
    、
    0.43
    ynomial
    0.43
     Crohn
    0.42
     Avner
    0.41
    島の
    0.41
    ?
    0.41
     μια
    0.41
    POSITIVE LOGITS
     спе
    0.62
    辏
    0.52
    橹
    0.48
    غان
    0.48
    त्रा
    0.47
    حان
    0.46
    茟
    0.46
    classteacher
    0.46
    agad
    0.46
    ن
    0.46
    Activations Density 0.000%

    No Known Activations