© 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. 110639
    Prev
    Next
    INDEX
    Explanations

    or all a to available part influenced

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

    initially becomes

    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
     rä
    0.64
    য়
    0.46
    uiden
    0.45
     mekan
    0.44
     উ
    0.43
    ”
    0.43
     radiology
    0.43
     Roosevelt
    0.42
    AVES
    0.41
    堯
    0.41
    POSITIVE LOGITS
    姹
    0.55
     አንዳንድ
    0.51
     այ
    0.48
    romptu
    0.48
    ές
    0.47
    aż
    0.47
    slidesPerGroup
    0.47
     agrade
    0.47
     expérience
    0.46
    밝
    0.46
    Activations Density 0.000%

    No Known Activations