© 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. 109794
    Prev
    Next
    INDEX
    Explanations

    possibly experience

    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
    Not in Any Lists

    No Comments

    Negative Logits
     intrig
    0.47
    킴
    0.45
     intimid
    0.44
    ступи
    0.43
     cheated
    0.43
     inm
    0.43
    بتدي
    0.42
     superstit
    0.42
     kane
    0.42
     superstitious
    0.42
    POSITIVE LOGITS
     ဝ
    0.45
     Mechanical
    0.44
    机械
    0.43
     sogen
    0.40
    Mechanical
    0.39
    传送
    0.39
     Վ
    0.39
     laughter
    0.38
     ആവശ്യ
    0.38
     Smiles
    0.38
    Activations Density 0.005%

    No Known Activations