© 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-TRANSCODER-262K
    7. 36685
    Prev
    Next
    INDEX
    Explanations

    "will not" fulfill

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
     fascism
    0.32
    뭡
    0.32
    ?“
    0.31
     bier
    0.30
    ན
    0.29
     held
    0.29
    Ⴖ
    0.29
    让她
    0.28
     milyon
    0.28
     mano
    0.28
    POSITIVE LOGITS
     whenever
    0.31
    ército
    0.30
     αί
    0.29
    వడం
    0.28
    传奇
    0.27
     pasted
    0.27
    ᄎ
    0.27
     documentación
    0.26
    uese
    0.26
    峹
    0.26
    Activations Density 0.039%

    No Known Activations