© 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. 216547
    Prev
    Next
    INDEX
    Explanations

    accepted for

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

    explaining why

    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
     ITA
    0.49
     already
    0.47
    裝
    0.46
    쯔
    0.45
     agre
    0.44
     Az
    0.43
     installer
    0.43
     +
    0.42
     only
    0.41
     shumë
    0.41
    POSITIVE LOGITS
    екси
    0.54
     Дон
    0.53
    Artifact
    0.51
    pessoa
    0.51
    вин
    0.50
    epochs
    0.50
    ynd
    0.49
    óa
    0.48
    seleccion
    0.47
    ករណ៍
    0.46
    Activations Density 0.000%

    No Known Activations