© 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. 133810
    Prev
    Next
    INDEX
    Explanations

    coconut oil

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

    explanations and guides

    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
    op
    0.55
    icular
    0.49
    origine
    0.46
    la
    0.46
    dashboard
    0.45
    uelos
    0.44
     insane
    0.44
    o
    0.44
    ve
    0.42
    issuer
    0.42
    POSITIVE LOGITS
    㐄
    0.59
    硣
    0.53
     Environments
    0.51
    夗
    0.49
     Schae
    0.48
    蒨
    0.48
     सेमेस्टर
    0.47
     Angebote
    0.47
    浥
    0.47
     materiale
    0.47
    Activations Density 0.000%

    No Known Activations