© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 5099
    Prev
    Next
    INDEX
    Explanations

    Science, air, best

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Kohn
    1.67
     vendita
    1.63
    obao
    1.62
    7
    1.56
    retail
    1.55
    8
    1.54
    9
    1.52
     lucht
    1.51
     comprar
    1.51
    avic
    1.49
    POSITIVE LOGITS
     historians
    1.93
    夫妇
    1.83
     adjustments
    1.70
     with
    1.70
    偕
    1.64
    舛
    1.63
     calendário
    1.62
    hoea
    1.59
    年は
    1.59
     reckons
    1.58
    Activations Density 0.000%

    No Known Activations