© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 162508
    Prev
    Next
    INDEX
    Explanations

    services reached

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

    LEGO, BI, css, Shirley, Progress, bricks

    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
    <unused226>
    0.53
    䣰
    0.52
    ű
    0.52
     ਤੁ
    0.50
     cysts
    0.50
     οικονομ
    0.50
     adaptarse
    0.50
    őt
    0.50
     chrys
    0.49
     inhibitors
    0.49
    POSITIVE LOGITS
    BE
    0.50
    </code>
    0.49
    2
    0.49
    Button
    0.47
    歌
    0.47
    Pra
    0.46
    방
    0.46
    Bag
    0.45
    方
    0.45
    NASA
    0.44
    Activations Density 0.000%

    No Known Activations