© 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. 174878
    Prev
    Next
    INDEX
    Explanations

    year of

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

    AutoTrain, acronym, rating, mode

    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
     പറ
    0.46
     సమయంలో
    0.46
    ットン
    0.44
    ပ
    0.44
    вел
    0.43
    劲
    0.43
    빴
    0.43
    樑
    0.43
    بار
    0.42
    부분
    0.42
    POSITIVE LOGITS
    asco
    0.50
    ổ
    0.47
    itates
    0.46
     gerar
    0.45
     progreso
    0.45
    asim
    0.45
    og
    0.45
    isión
    0.45
    aside
    0.43
    drinks
    0.43
    Activations Density 0.000%

    No Known Activations