© 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. 204219
    Prev
    Next
    INDEX
    Explanations

    Blade, infrastructure, sentimental

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

    API insights License

    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
     digitale
    0.49
    テゴ
    0.48
     stderr
    0.46
     nonchal
    0.46
    uffix
    0.45
     zee
    0.45
     WORDS
    0.43
    ｕ
    0.43
    นะคะ
    0.42
    اخ
    0.42
    POSITIVE LOGITS
    Pis
    0.51
    FieldIndex
    0.49
    Bac
    0.46
     bunt
    0.46
    AFP
    0.45
    Rig
    0.45
     ihtiyaç
    0.45
    streng
    0.45
    Blueprint
    0.45
    kanı
    0.44
    Activations Density 0.000%

    No Known Activations