© 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. 39460
    Prev
    Next
    INDEX
    Explanations

    question marks and periods

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

    words starting and ending with letters

    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
    Koordin
    0.41
    वे
    0.40
    汞
    0.39
    ئا
    0.39
    犢
    0.39
    âche
    0.39
    稹
    0.39
    萱
    0.37
    ⎢
    0.37
    خر
    0.37
    POSITIVE LOGITS
     spi
    0.44
    したい
    0.43
     popraw
    0.39
     spectre
    0.38
     বহুম
    0.38
     genomic
    0.38
     unis
    0.38
     ROT
    0.37
     improvement
    0.37
    pu
    0.37
    Activations Density 0.015%

    No Known Activations