© 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. 35983
    Prev
    Next
    INDEX
    Explanations

    president Kevin

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

    needed, been, with

    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
     appendices
    0.53
     genotype
    0.51
     underpinned
    0.49
    );
    0.47
     investigated
    0.47
     Álvarez
    0.45
     investigates
    0.45
    ।
    0.45
     overlapped
    0.44
     論
    0.44
    POSITIVE LOGITS
    S
    0.54
    M
    0.53
    R
    0.52
    B
    0.50
    L
    0.48
    Liber
    0.46
    C
    0.46
    V
    0.46
    咨询
    0.45
    邮
    0.45
    Activations Density 0.001%

    No Known Activations