© 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. 16-GEMMASCOPE-2-RES-262K
    7. 107418
    Prev
    Next
    INDEX
    Explanations

    You're speaking my language

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     nella
    0.49
    Euph
    0.47
    dalam
    0.47
    )]);
    0.47
     populer
    0.45
    klad
    0.44
    ISSN
    0.44
    appeared
    0.44
     നിറ
    0.44
    difference
    0.43
    POSITIVE LOGITS
    控制
    0.54
     ép
    0.50
     semana
    0.49
     esk
    0.49
    _=
    0.49
     intimidate
    0.48
     campañas
    0.48
     bancos
    0.48
     agencia
    0.47
     feas
    0.46
    Activations Density 0.000%

    No Known Activations