© 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. 133752
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptions

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

    specific contexts or considerations

    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
     مقابلے
    0.43
     neues
    0.43
     場
    0.42
     pluripotent
    0.41
     Hey
    0.41
    ご紹介
    0.40
     روک
    0.40
     那麼
    0.40
     proteínas
    0.39
    ప్రత్యర్థి
    0.39
    POSITIVE LOGITS
    cinn
    0.49
    ल्यावर
    0.47
     vremena
    0.46
     brev
    0.45
    ить
    0.45
    ജ
    0.44
    ùm
    0.44
    items
    0.44
     dziel
    0.44
    品番
    0.43
    Activations Density 0.001%

    No Known Activations