© 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. 131325
    Prev
    Next
    INDEX
    Explanations

    offering a, find crafts, need, comment and, assists training, speed of

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

    Doctor Finch

    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
    N
    0.50
    פ
    0.50
    咂
    0.46
    ड
    0.46
    ᆫ
    0.45
    प
    0.44
    Legal
    0.44
    Dys
    0.44
    탓
    0.44
    כב
    0.43
    POSITIVE LOGITS
     করিয়াছে
    0.52
     teor
    0.52
     policym
    0.49
    与其
    0.49
     menyediakan
    0.48
     tersebut
    0.47
     Poincaré
    0.47
     Teor
    0.47
     lui
    0.46
     उत्तरा
    0.46
    Activations Density 0.000%

    No Known Activations