© 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. 56664
    Prev
    Next
    INDEX
    Explanations

    original notice

    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
    ası
    0.53
    ूल
    0.52
     Epistle
    0.46
    specifiedByURL
    0.45
    }^{*}(\
    0.44
    ТУ
    0.44
    us
    0.44
    ूफ
    0.43
     Micros
    0.43
     Studios
    0.42
    POSITIVE LOGITS
     narrowing
    0.55
     scom
    0.54
     nao
    0.54
     sapere
    0.54
     question
    0.53
     high
    0.52
     noto
    0.51
     answer
    0.51
     compat
    0.51
    かどうか
    0.51
    Activations Density 0.002%

    No Known Activations