© 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. 41434
    Prev
    Next
    INDEX
    Explanations

    cooking instructions

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

    metrics and preparation instructions

    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
     मिस
    0.51
    უ
    0.46
    uma
    0.45
    zata
    0.44
     మి
    0.43
     बिग
    0.42
    关
    0.42
     Majesty
    0.42
    湪
    0.41
    Mia
    0.41
    POSITIVE LOGITS
     поро
    0.49
     mutagenesis
    0.47
     теор
    0.46
     pathological
    0.43
     дослід
    0.43
     exhaustive
    0.42
     pathologists
    0.41
    \".
    0.41
     impenetr
    0.40
    поро
    0.40
    Activations Density 0.000%

    No Known Activations