© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 172708
    Prev
    Next
    INDEX
    Explanations

    aspects of, easily pick

    np_acts-logits-general · gemini-2.5-flash-lite

    providing or providing with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     éclair
    0.50
    軐
    0.47
     были
    0.46
    Repo
    0.45
    éclair
    0.45
    ж
    0.45
     ಎಷ್ಟು
    0.45
    嗰
    0.45
    တို့
    0.44
     жили
    0.44
    POSITIVE LOGITS
     your
    0.53
     swipes
    0.49
     middlewares
    0.49
     tickets
    0.48
     sandpaper
    0.47
     midfielders
    0.46
     swabs
    0.46
     platforms
    0.46
     mediates
    0.44
     hikes
    0.44
    Activations Density 0.001%

    No Known Activations