© 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. 212852
    Prev
    Next
    INDEX
    Explanations

    precious stones

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

    buy, Dead, de, ordin

    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
    Gosudarstvennyj
    0.12
    <unused1057>
    0.12
    ന്വേഷ
    0.11
    <unused1019>
    0.11
     persec
    0.10
    လိုအပ်
    0.10
    <unused444>
    0.10
     bactéries
    0.10
    <unused1048>
    0.10
     sécrétion
    0.10
    POSITIVE LOGITS
    /
    0.14
    and
    0.14
     (
    0.12
    (
    0.12
    -
    0.12
    D
    0.12
     and
    0.12
    L
    0.12
     &
    0.11
    in
    0.11
    Activations Density 0.000%

    No Known Activations