© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 59246
    Prev
    Next
    INDEX
    Explanations

    match the

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

    matches the

    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
     eſ
    0.51
    일
    0.51
    ῃ
    0.51
     mă
    0.50
    できる
    0.49
     فی
    0.49
    đu
    0.49
     بداية
    0.48
     į
    0.48
     méthodes
    0.48
    POSITIVE LOGITS
     Grover
    0.51
     Foreman
    0.50
     Gastroenter
    0.46
     Just
    0.44
     Dok
    0.43
     If
    0.43
     Jeb
    0.43
     Deck
    0.42
     Outreach
    0.42
     Rich
    0.42
    Activations Density 0.006%

    No Known Activations