© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 111825
    Prev
    Next
    INDEX
    Explanations

    instructions or descriptions

    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
     сигна
    0.39
     Connell
    0.37
    ੪
    0.37
     sqlite
    0.36
     assigned
    0.35
    кой
    0.35
     স্কুল
    0.35
     axis
    0.35
     sauce
    0.35
    als
    0.35
    POSITIVE LOGITS
    eve
    0.42
    assertArg
    0.42
    APPROVAL
    0.39
     gradioApp
    0.38
    Artwork
    0.38
    <h6>
    0.38
    igrams
    0.37
    buffered
    0.37
    楲
    0.37
    THE
    0.37
    Activations Density 0.000%

    No Known Activations