© 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. 106978
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    skeletons ever go on dates

    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
     Adaptive
    0.46
     pp
    0.45
     neurop
    0.43
     ppl
    0.43
     scipy
    0.43
     Fern
    0.43
     吴
    0.43
     则
    0.43
     instytuc
    0.42
     Room
    0.42
    POSITIVE LOGITS
    žeme
    0.47
    シェア
    0.44
    ुआ
    0.43
    agamo
    0.43
    ちなみに
    0.43
    faite
    0.42
    ída
    0.42
    えています
    0.42
    ちょっと
    0.41
    リート
    0.41
    Activations Density 0.001%

    No Known Activations