© 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. 209834
    Prev
    Next
    INDEX
    Explanations

    four model

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

    chat conversations interactions

    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
    🧗
    0.51
    أ
    0.49
    Baltimore
    0.49
    А
    0.46
    М
    0.46
    Τ
    0.46
     Komponenten
    0.46
    M
    0.46
    Это
    0.45
    টেন
    0.45
    POSITIVE LOGITS
    dd
    0.50
     sanguí
    0.47
    z
    0.47
    ias
    0.46
    assi
    0.46
    ng
    0.45
    permission
    0.45
    ogran
    0.45
    ani
    0.44
    ne
    0.44
    Activations Density 0.000%

    No Known Activations