© 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. 101267
    Prev
    Next
    INDEX
    Explanations

    help and information

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

    magical realism

    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
    散
    0.56
     будь
    0.52
    我們
    0.52
    ৱ
    0.52
    規
    0.50
    project
    0.49
    事を
    0.49
     हाउस
    0.49
    "
    0.49
    part
    0.48
    POSITIVE LOGITS
     Soph
    0.47
     adaptor
    0.46
     Lâm
    0.45
     nā
    0.45
     Levin
    0.45
     점점
    0.44
    ایی
    0.44
     çöz
    0.44
     invertible
    0.43
    kowych
    0.43
    Activations Density 0.000%

    No Known Activations