© 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. 249617
    Prev
    Next
    INDEX
    Explanations

    quantities and measurements

    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
    rees
    0.44
    ę
    0.44
    determination
    0.44
    是的
    0.43
    Relatives
    0.43
    요일
    0.43
    temporary
    0.43
    kt
    0.42
    rien
    0.42
    å
    0.42
    POSITIVE LOGITS
    俎
    0.49
    ="...">
    0.47
    береж
    0.45
    লোকে
    0.45
     pourrez
    0.45
    краё
    0.43
    osaur
    0.43
     использу
    0.43
    古屋
    0.43
    \|_{
    0.42
    Activations Density 0.001%

    No Known Activations