© 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. 205576
    Prev
    Next
    INDEX
    Explanations

    voxel, probabilities, suffers

    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
    v
    0.54
    upani
    0.52
    لمان
    0.50
    jl
    0.49
    vans
    0.49
    vano
    0.48
    كة
    0.48
     Âu
    0.47
     musculaire
    0.45
    ioane
    0.44
    POSITIVE LOGITS
    ί
    0.61
    ი
    0.54
    י
    0.53
     decidió
    0.46
     střed
    0.45
     acuerdo
    0.44
     colores
    0.44
    颜色
    0.44
    抗
    0.44
    第一
    0.44
    Activations Density 0.000%

    No Known Activations