© 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. 2980
    Prev
    Next
    INDEX
    Explanations

    JSON processing and generation parameters

    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
     máxima
    0.52
     selecion
    0.49
     approbation
    0.48
     cicat
    0.47
    }_{(
    0.44
     seleccionar
    0.44
     rechaz
    0.44
     sanguin
    0.44
     plana
    0.43
     contenedor
    0.43
    POSITIVE LOGITS
     εται
    0.47
    awi
    0.46
     ପ୍ର
    0.44
    airobi
    0.41
    ahan
    0.40
    衰
    0.40
    ollow
    0.39
    aji
    0.39
    unku
    0.39
    ıs
    0.39
    Activations Density 0.003%

    No Known Activations