© 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. 31-GEMMASCOPE-2-RES-262K
    7. 202243
    Prev
    Next
    INDEX
    Explanations

    secretly adding or finding

    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_31_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
     посредством
    0.49
    ură
    0.46
     angem
    0.45
     ausgew
    0.45
    ofd
    0.44
    স্বপ
    0.44
     значи
    0.43
    譞
    0.43
    agé
    0.43
    ктор
    0.43
    POSITIVE LOGITS
    u
    0.52
    helpers
    0.47
    するのが
    0.47
     assassination
    0.45
     corruption
    0.44
    '),
    0.44
    ')
    0.43
     selector
    0.42
    corruption
    0.42
    メーカー
    0.41
    Activations Density 0.014%

    No Known Activations