© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 31593
    Prev
    Next
    INDEX
    Explanations

    contacting people

    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
    Negative Logits
    其他
    0.47
     επίσης
    0.43
     తెలిపారు
    0.42
     empfohlen
    0.42
    órmula
    0.39
    后再
    0.39
    輕鬆
    0.38
     குறித்து
    0.38
    ipo
    0.38
    高
    0.38
    POSITIVE LOGITS
     inextricably
    0.46
    hubungan
    0.44
    사람
    0.43
     heterosexual
    0.41
    ርስዎ
    0.41
     natively
    0.41
     entw
    0.41
     sexe
    0.41
     prostitutes
    0.41
     bureaucrats
    0.40
    Activations Density 0.002%

    No Known Activations