© 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. 31-GEMMASCOPE-2-RES-262K
    7. 101393
    Prev
    Next
    INDEX
    Explanations

    information or instructions

    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_31_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
     selling
    0.46
     repug
    0.46
     philos
    0.46
     밖에
    0.44
     sada
    0.44
     souci
    0.44
    竰
    0.44
    чивать
    0.44
     poważ
    0.44
     explic
    0.43
    POSITIVE LOGITS
    reas
    0.47
    $&
    0.45
     சூ
    0.43
    .
    0.43
     живот
    0.43
    Info
    0.42
    info
    0.41
     apert
    0.41
    按摩
    0.41
    ningar
    0.41
    Activations Density 0.004%

    No Known Activations