© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8485
    Prev
    Next
    INDEX
    Explanations

    actionable predictors

    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
     Ե
    0.54
     അടിസ്ഥാന
    0.54
    欱
    0.53
     dłu
    0.52
     Verantwort
    0.51
     企业
    0.51
     Phương
    0.50
     Unternehmens
    0.48
    ają
    0.47
     Elis
    0.47
    POSITIVE LOGITS
    </h2>
    0.46
     subpar
    0.43
    ्यू
    0.42
     screenings
    0.42
     predictor
    0.41
     regulators
    0.41
    \
    0.41
     radiographs
    0.41
     predictors
    0.40
     actionable
    0.40
    Activations Density 0.013%

    No Known Activations