© 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. 107516
    Prev
    Next
    INDEX
    Explanations

    organizations, places, and processes

    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
     maturation
    0.51
    లం
    0.50
    దం
    0.50
    विज्ञान
    0.49
    （
    0.49
    )*
    0.49
    動
    0.49
    灘
    0.48
    )*(
    0.48
     متغير
    0.48
    POSITIVE LOGITS
     ganado
    0.48
    ou
    0.47
     rado
    0.47
    us
    0.46
    aula
    0.46
    ्ज
    0.46
    as
    0.46
     resalt
    0.45
    و
    0.45
    amad
    0.44
    Activations Density 0.000%

    No Known Activations