© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50598
    Prev
    Next
    INDEX
    Explanations

    question:

    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_40_width_65k_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
     criação
    0.44
     buena
    0.42
     creare
    0.42
    amic
    0.41
    繪
    0.41
     reusing
    0.40
    ddd
    0.39
    sing
    0.39
     yarat
    0.38
     scrivere
    0.38
    POSITIVE LOGITS
    CONTEXT
    0.46
    iciens
    0.40
    答
    0.38
    फत
    0.38
    IR
    0.38
    鍗
    0.37
    imbledon
    0.36
    RIE
    0.36
    ométrique
    0.35
    COMMENT
    0.34
    Activations Density 0.004%

    No Known Activations