© 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. 40-GEMMASCOPE-2-RES-262K
    7. 137561
    Prev
    Next
    INDEX
    Explanations

    government, implied, connectivity, exits, inclusive

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     reactant
    0.42
    一定的
    0.41
    zón
    0.38
    零件
    0.38
     തോന്ന
    0.38
     tiềm
    0.38
    颠
    0.38
     масшта
    0.37
    ⿸
    0.37
    ទុក
    0.37
    POSITIVE LOGITS
     scar
    0.40
     prostitute
    0.40
     dieta
    0.39
    angry
    0.39
    itle
    0.38
    rae
    0.38
     raven
    0.38
     pleasures
    0.38
     sullen
    0.38
     insulted
    0.38
    Activations Density 0.001%

    No Known Activations