© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 45384
    Prev
    Next
    INDEX
    Explanations

    dedicated account

    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_65k_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
    ্র
    0.42
     plut
    0.42
    2
    0.42
    revenue
    0.41
     Montgomery
    0.41
     snoring
    0.40
    -
    0.40
    "
    0.40
    ＋
    0.39
     town
    0.39
    POSITIVE LOGITS
     сезон
    0.54
     пе
    0.52
     риска
    0.52
    Issledovatel
    0.52
     riesgos
    0.51
     перспекти
    0.51
     сезо
    0.49
     diversidad
    0.48
     раство
    0.48
     SEASON
    0.47
    Activations Density 0.021%

    No Known Activations