© 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. 223917
    Prev
    Next
    INDEX
    Explanations

    likely then, each shoot, has a

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

    overall theme or context

    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
     or
    0.43
    👬
    0.42
     Smile
    0.42
     Strings
    0.42
     icch
    0.41
     botan
    0.40
     aau
    0.40
     idk
    0.40
     juicy
    0.40
     czyli
    0.39
    POSITIVE LOGITS
     забруд
    0.50
    灏
    0.48
    消毒
    0.48
     लावा
    0.47
     हटाने
    0.46
    activeIndex
    0.46
     карбо
    0.46
    Firefox
    0.46
    catalyzed
    0.45
     कार्बन
    0.45
    Activations Density 0.000%

    No Known Activations