© 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. 91370
    Prev
    Next
    INDEX
    Explanations

    non-english and specific terms

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

    topics discussed

    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
     Cinema
    0.48
    PU
    0.42
     reciproc
    0.42
     Best
    0.39
     ."
    0.39
    ↵↵
    0.39
    LA
    0.39
    PL
    0.39
    USA
    0.39
     LF
    0.39
    POSITIVE LOGITS
    खाली
    0.62
     quieras
    0.57
    pendiente
    0.56
    ='',
    0.55
    परेट
    0.55
     objectionable
    0.54
     unacceptable
    0.53
     intolerable
    0.53
     cięż
    0.52
     आइड
    0.52
    Activations Density 0.000%

    No Known Activations