© 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. 152955
    Prev
    Next
    INDEX
    Explanations

    generators, graphics, solutions

    np_acts-logits-general · gemini-2.5-flash-lite

    refusal due to safety guidelines

    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
     CII
    0.51
     During
    0.48
     संरक्षित
    0.47
     पेपर
    0.46
     논
    0.45
    arif
    0.45
    dispers
    0.45
     surcharge
    0.44
     Two
    0.42
     Along
    0.41
    POSITIVE LOGITS
    ]$
    0.51
     estrellas
    0.49
     králov
    0.49
     máte
    0.44
    ധികം
    0.44
     aprobación
    0.43
     obses
    0.43
     sevgili
    0.42
     impegno
    0.42
    ᶰ
    0.42
    Activations Density 0.001%

    No Known Activations