© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202146
    Prev
    Next
    INDEX
    Explanations

    intercepts intents and requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arbeiten
    0.48
     Slovens
    0.46
     <=
    0.45
     Ernährung
    0.45
     groupBy
    0.42
     Infine
    0.42
     Eng
    0.42
     Endpoint
    0.42
     matr
    0.41
     =
    0.41
    POSITIVE LOGITS
    قوم
    0.49
    ವಾರು
    0.47
     ಕೂ
    0.47
    riot
    0.45
    omata
    0.45
    otas
    0.45
    ится
    0.45
    ಿಯಾ
    0.43
    atiques
    0.43
    ята
    0.43
    Activations Density 0.002%

    No Known Activations