© 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. 252530
    Prev
    Next
    INDEX
    Explanations

    years after start

    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
    北美
    0.42
    amn
    0.41
    animals
    0.40
     bigotry
    0.40
    digest
    0.40
    ｄ
    0.40
    touchstart
    0.39
    firefox
    0.39
    d
    0.39
    statements
    0.38
    POSITIVE LOGITS
     cuando
    0.48
     encara
    0.45
     tavolo
    0.44
     chưa
    0.44
     Desarrollo
    0.44
     כאשר
    0.44
     utilizzo
    0.42
     How
    0.42
     belum
    0.42
     vieja
    0.42
    Activations Density 0.000%

    No Known Activations