© 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. 55395
    Prev
    Next
    INDEX
    Explanations

    pentagonal logo

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

    numbers and specific words

    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
     Altman
    0.47
    复制代码
    0.46
     Goldberg
    0.42
     Pollock
    0.42
     Window
    0.42
     Ayala
    0.42
    Еще
    0.42
    ="
    0.41
     Malone
    0.39
     Al
    0.38
    POSITIVE LOGITS
    onents
    0.48
    ormais
    0.46
     rurales
    0.46
    ライズ
    0.45
    การณ์
    0.44
    🏍
    0.43
    報道
    0.43
    হাম্মদ
    0.43
     vytvá
    0.43
    ὲ
    0.43
    Activations Density 0.000%

    No Known Activations