© 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-262K
    7. 129180
    Prev
    Next
    INDEX
    Explanations

    input machine or process

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     수
    0.44
    luss
    0.42
     संभावना
    0.41
    ianza
    0.41
    S
    0.40
     He
    0.40
    ০০
    0.39
     Noor
    0.39
     S
    0.39
     जान
    0.38
    POSITIVE LOGITS
     catalogues
    0.51
    デイ
    0.49
    eOut
    0.49
    ൨
    0.49
    ཥ
    0.48
    第壹百
    0.47
    ccgi
    0.46
    бы
    0.45
    ɳ
    0.45
    ಮ
    0.45
    Activations Density 0.001%

    No Known Activations