© 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. 89623
    Prev
    Next
    INDEX
    Explanations

    charitable solutions and brilliance

    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
     scanty
    0.49
     chiefly
    0.47
     tyres
    0.46
     tyre
    0.44
     영국
    0.44
     organiser
    0.43
    伴
    0.41
     instalments
    0.40
     reassuring
    0.40
     diarrhoea
    0.40
    POSITIVE LOGITS
    OH
    0.44
     кван
    0.43
     Planetary
    0.43
     вдох
    0.42
    getVisibility
    0.42
     🙏
    0.41
     сопротив
    0.41
    🌎
    0.41
     Согласно
    0.41
    总统
    0.40
    Activations Density 0.004%

    No Known Activations