© 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. 2508
    Prev
    Next
    INDEX
    Explanations

    a followed by a specific descriptor

    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
     approximately
    0.18
     considerably
    0.18
    <0xE2>
    0.17
     extremely
    0.16
     substantially
    0.16
     quite
    0.16
     extensively
    0.15
     상당히
    0.15
     [(
    0.15
     the
    0.15
    POSITIVE LOGITS
     solche
    0.18
     vraie
    0.18
     solchen
    0.18
     dodgy
    0.17
     lefty
    0.17
     crappy
    0.17
     sinner
    0.17
     glimpse
    0.17
     hunch
    0.17
     οπο
    0.16
    Activations Density 0.481%

    No Known Activations