© 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-65K
    7. 63291
    Prev
    Next
    INDEX
    Explanations

    job search websites

    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
     selezione
    0.47
    Technische
    0.43
     seleção
    0.43
     paylaş
    0.41
    '}}>
    0.41
    Ŭ
    0.40
    Selection
    0.40
    '})
    0.40
     ગ્ર
    0.39
     মুক্তিব
    0.39
    POSITIVE LOGITS
    經驗
    0.39
     Houston
    0.38
     Estimated
    0.38
    chelon
    0.38
     BMX
    0.37
    cador
    0.37
     Mail
    0.36
     end
    0.36
     FedEx
    0.36
     Delta
    0.36
    Activations Density 0.030%

    No Known Activations