© 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. 243945
    Prev
    Next
    INDEX
    Explanations

    academic papers, dates, and facts

    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
     तेज़
    0.52
    ooq
    0.47
    т
    0.47
    avali
    0.46
     refuer
    0.46
    imak
    0.45
    ımda
    0.45
    tbx
    0.44
    aio
    0.44
    endimento
    0.44
    POSITIVE LOGITS
     +
    0.54
     Nietzsche
    0.47
     delusion
    0.45
     pagination
    0.45
     मांगा
    0.45
    ').
    0.44
     humanity
    0.44
     nonfiction
    0.43
     seventh
    0.43
     relationship
    0.43
    Activations Density 0.001%

    No Known Activations