© 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. 143100
    Prev
    Next
    INDEX
    Explanations

    attempt to

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

    AI speed optimization

    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
     equate
    0.54
    evening
    0.53
    t
    0.53
     evening
    0.50
     intervals
    0.50
     headers
    0.48
    ㄌ
    0.46
    辑
    0.46
     <
    0.46
    了
    0.46
    POSITIVE LOGITS
    গঠনিক
    0.45
     Venetian
    0.45
    isphere
    0.45
    ianza
    0.43
     Alliance
    0.43
    convergence
    0.43
    zana
    0.42
     सास
    0.42
    وریت
    0.42
     Borussia
    0.42
    Activations Density 0.001%

    No Known Activations