© 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. 5215
    Prev
    Next
    INDEX
    Explanations

    success words

    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
     odio
    1.59
     memperhatikan
    1.52
     ',');
    1.47
    intah
    1.46
     Penit
    1.45
    alaikumsalam
    1.44
    แยก
    1.41
    เวลา
    1.39
    怜
    1.39
     binatang
    1.37
    POSITIVE LOGITS
     promising
    1.41
     ambitious
    1.36
     launching
    1.34
     launched
    1.32
     promotion
    1.32
     exciting
    1.32
     suave
    1.29
     innovation
    1.28
     innovative
    1.28
     innov
    1.28
    Activations Density 0.005%

    No Known Activations