© 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. 80959
    Prev
    Next
    INDEX
    Explanations

    instructions and negation

    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
    -
    0.60
     vel
    0.43
    с
    0.43
    ,
    0.42
     sweater
    0.41
    yler
    0.41
    ientemente
    0.41
    /
    0.41
     skills
    0.40
    skills
    0.39
    POSITIVE LOGITS
     Describes
    0.48
    Health
    0.47
     Palo
    0.46
    Clinic
    0.46
     Greensboro
    0.45
    Crow
    0.45
    餑
    0.45
    Closeup
    0.44
     Escuela
    0.44
    ༼
    0.44
    Activations Density 0.008%

    No Known Activations