© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 229651
    Prev
    Next
    INDEX
    Explanations

    biological components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     unending
    0.50
     brasileiro
    0.46
     जिसने
    0.45
     francês
    0.44
     Grec
    0.43
     administr
    0.43
    }$,
    0.42
     Indiana
    0.42
    political
    0.42
     Serbian
    0.41
    POSITIVE LOGITS
     ንጥረ
    0.51
    능
    0.49
     gula
    0.49
     lipids
    0.46
     follicles
    0.45
     אפ
    0.45
     lawns
    0.44
    纤维
    0.44
     minerals
    0.44
    את
    0.44
    Activations Density 0.000%

    No Known Activations