© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12640
    Prev
    Next
    INDEX
    Explanations

    emphasis or exceptions

    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_40_width_262k_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
     mostly
    0.24
     fixes
    0.22
     Orange
    0.22
     sets
    0.21
     OSI
    0.21
     encompassing
    0.21
     tasked
    0.20
    -
    0.20
     user
    0.20
     looking
    0.20
    POSITIVE LOGITS
     ceux
    0.24
     вследствие
    0.23
     socalled
    0.22
    during
    0.21
     cosidd
    0.21
    RELATIVA
    0.21
     aquellos
    0.20
    those
    0.20
    necessarily
    0.20
     مثلا
    0.20
    Activations Density 0.047%

    No Known Activations