© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2216
    Prev
    Next
    INDEX
    Explanations

    Google DeepMind creators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    即使
    0.44
    PGS
    0.42
    </h3>
    0.40
    ...!
    0.39
    %!
    0.38
    !);
    0.38
    ！」
    0.37
    !;
    0.37
     Или
    0.37
    ទ្រ
    0.36
    POSITIVE LOGITS
     असून
    0.80
     but
    0.71
     लेकिन
    0.70
     nhưng
    0.70
    ですが
    0.68
     אבל
    0.67
     لكن
    0.67
    but
    0.66
    लेकिन
    0.66
     কিন্তু
    0.64
    Activations Density 0.528%

    No Known Activations