© 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. 241720
    Prev
    Next
    INDEX
    Explanations

    technical standards and chance

    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
    न
    0.52
    ن
    0.51
    ल
    0.48
    FOUR
    0.48
    ர
    0.48
    zeugt
    0.47
    Sí
    0.46
    ぼ
    0.46
     proporcion
    0.46
    chten
    0.45
    POSITIVE LOGITS
    ulfillment
    0.46
     Parmesan
    0.42
    outfile
    0.41
     LOC
    0.41
    ulosa
    0.40
    粞
    0.39
     પોલી
    0.39
     डेवलपमेंट
    0.39
    遗
    0.38
     cosi
    0.38
    Activations Density 0.001%

    No Known Activations