© 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-16K
    7. 11554
    Prev
    Next
    INDEX
    Explanations

    questions about, tailoring or, plunge into

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

    offering alternatives or suggestions

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     veya
    0.48
     totiž
    0.44
     หรือ
    0.43
     nämlich
    0.43
     असल्याची
    0.43
    🫰
    0.43
     असल्याचे
    0.42
    یعنی
    0.42
     یعنی
    0.41
     म्हणजे
    0.41
    POSITIVE LOGITS
     ;
    0.45
    ;
    0.45
    ;
    0.40
    --;
    0.40
    ]$;
    0.40
    ；
    0.39
    那我們
    0.39
     això
    0.38
    _;
    0.38
    $;
    0.38
    Activations Density 0.567%

    No Known Activations