© 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. 251892
    Prev
    Next
    INDEX
    Explanations

    explain why, sales handmade, foreign powers, immediate recomp

    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
    ুতি
    0.46
    াং
    0.44
    راب
    0.42
    s
    0.42
    UN
    0.41
    ului
    0.41
    IN
    0.40
     {})
    0.40
    a
    0.40
     ...)
    0.39
    POSITIVE LOGITS
    വില്‍
    0.55
     ngôn
    0.52
     popraw
    0.52
     fandom
    0.50
     पार्टी
    0.50
    emitter
    0.49
     automáticamente
    0.49
     bằng
    0.48
     टैक्स
    0.47
     aceptación
    0.47
    Activations Density 0.001%

    No Known Activations