© 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. 188639
    Prev
    Next
    INDEX
    Explanations

    screening, monitoring, couch, aming

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

    knowledge cutoff

    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
     coercion
    0.52
     ignore
    0.50
     errands
    0.50
     दूरसंचार
    0.50
     absol
    0.48
     ます
    0.48
    >`,
    0.48
     forgiven
    0.48
     こちら
    0.47
    ियन
    0.47
    POSITIVE LOGITS
    ців
    0.53
    촌
    0.51
    IN
    0.49
    ститут
    0.48
    a
    0.48
    ای
    0.46
    掌
    0.45
    цева
    0.45
    물
    0.45
     Rapport
    0.45
    Activations Density 0.001%

    No Known Activations