© 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. 249766
    Prev
    Next
    INDEX
    Explanations

    is followed by numerical or descriptive states

    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
    ángulos
    0.42
     curvatures
    0.41
     окре
    0.40
    ዃ
    0.39
    पेड
    0.39
    বাহ
    0.38
     अध्या
    0.38
     calves
    0.38
    allas
    0.37
    ITATION
    0.37
    POSITIVE LOGITS
     (+
    0.41
     রাত
    0.41
     දු
    0.40
     HQ
    0.40
     Pandit
    0.40
     Brexit
    0.39
    বিচার
    0.39
     গভর্নর
    0.39
     regime
    0.39
    機関
    0.39
    Activations Density 0.004%

    No Known Activations