© 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. 226726
    Prev
    Next
    INDEX
    Explanations

    how greedy, burn anything, so long, that they

    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
     வேண்டுமெ
    0.50
    رسی
    0.45
     شهد
    0.45
    島の
    0.44
    у
    0.44
    anmoins
    0.43
    ुल्लाह
    0.42
     angulis
    0.41
    짧
    0.41
     돌아
    0.41
    POSITIVE LOGITS
     talento
    0.53
     Abril
    0.47
     PUC
    0.47
     caro
    0.45
     Tn
    0.45
     euros
    0.45
     pera
    0.45
     bhan
    0.45
     maio
    0.45
     والش
    0.44
    Activations Density 0.001%

    No Known Activations