© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73212
    Prev
    Next
    INDEX
    Explanations

    plugin, thesis, foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    吅
    -1.21
    providedIn
    -1.16
    файл
    -1.16
    那时
    -1.13
    那时候
    -1.13
     آن‌ها
    -1.06
    入れた
    -1.05
     Hinsicht
    -1.05
    尔斯
    -1.04
    rassing
    -1.02
    POSITIVE LOGITS
     můžete
    1.42
    现在
    1.31
     vuelve
    1.30
     empieza
    1.26
     volverá
    1.25
     comienza
    1.22
     reconoce
    1.20
     mantend
    1.19
     může
    1.18
     není
    1.15
    Activations Density 0.015%

    No Known Activations