© 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. 217884
    Prev
    Next
    INDEX
    Explanations

    uploaded and published

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

    danger, barrier

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ker
    0.54
    ke
    0.52
    el
    0.50
    1
    0.50
    org
    0.49
    ce
    0.47
    ya
    0.46
    ago
    0.46
    4
    0.46
    ala
    0.45
    POSITIVE LOGITS
     cân
    0.55
     condição
    0.53
     provoqu
    0.52
     bút
    0.51
     phénom
    0.50
     antivirus
    0.50
     exécut
    0.50
     cárc
    0.49
     hypoth
    0.49
     indústria
    0.48
    Activations Density 0.000%

    No Known Activations