© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 132466
    Prev
    Next
    INDEX
    Explanations

    current, survival, pink, detail, colossal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    䝬
    0.46
     밖에
    0.45
     spéc
    0.42
     まで
    0.41
     الحالة
    0.41
     مفید
    0.40
     работода
    0.40
     బ్రిటిష్
    0.40
    बिर
    0.40
    ძლიათ
    0.39
    POSITIVE LOGITS
    FXML
    0.41
    colon
    0.41
    LICENSE
    0.39
    index
    0.39
    @]
    0.38
    as
    0.38
    predictor
    0.38
    ologe
    0.38
    incremental
    0.38
    und
    0.37
    Activations Density 0.000%

    No Known Activations