© 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. 12055
    Prev
    Next
    INDEX
    Explanations

    word replacements or additions

    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
    ête
    0.38
    </h1>
    0.36
    ion
    0.36
    ud
    0.36
    uent
    0.36
    uite
    0.36
    iect
    0.35
    wati
    0.35
     Tribe
    0.35
     ев
    0.35
    POSITIVE LOGITS
    为例
    0.44
    作为一个
    0.44
     itself
    0.43
    作為
    0.41
     作为
    0.38
    作为
    0.37
    邂
    0.37
     notoriously
    0.36
    它的
    0.36
     intervenir
    0.36
    Activations Density 0.158%

    No Known Activations