© 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. 223844
    Prev
    Next
    INDEX
    Explanations

    cardholder terms

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

    articulate, type, tell

    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
     ui
    0.52
     vendeur
    0.49
    뭇
    0.49
     escal
    0.47
    ң
    0.47
    ל
    0.47
    蔬
    0.46
     danske
    0.46
    чев
    0.46
    ربعة
    0.46
    POSITIVE LOGITS
    Ket
    0.48
    shaped
    0.46
     pensamiento
    0.45
    Im
    0.45
    organ
    0.44
    November
    0.44
    population
    0.43
     Theology
    0.43
    ”
    0.43
     চাপে
    0.42
    Activations Density 0.000%

    No Known Activations