© 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. 163407
    Prev
    Next
    INDEX
    Explanations

    lug nuts, branch piping, network certified

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

    audience overload, met with, formation of

    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
    Tera
    0.47
     Жен
    0.47
    鼐
    0.45
    臧
    0.45
    Bon
    0.44
    Emily
    0.44
    Notation
    0.44
     Če
    0.44
     Notation
    0.44
     Moderator
    0.42
    POSITIVE LOGITS
     allemand
    0.46
    諒
    0.44
     permettant
    0.44
    ラ
    0.42
    に向け
    0.41
    ین
    0.41
    گان
    0.41
     permiten
    0.41
    ोदय
    0.41
    ған
    0.40
    Activations Density 0.002%

    No Known Activations