© 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-16K
    7. 12148
    Prev
    Next
    INDEX
    Explanations

    with and without

    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_16k_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
    BLE
    0.36
     thing
    0.35
    >[
    0.33
    <strong>
    0.32
    Actually
    0.32
     *
    0.32
    нче
    0.32
    <sup>
    0.31
    >`,
    0.31
    ashvili
    0.31
    POSITIVE LOGITS
     without
    0.78
     with
    0.75
    without
    0.66
     χωρίς
    0.64
     посредством
    0.63
    with
    0.61
     dengan
    0.61
     với
    0.59
    程度上
    0.59
     via
    0.59
    Activations Density 0.411%

    No Known Activations