© 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. 108985
    Prev
    Next
    INDEX
    Explanations

    activity and study outcomes

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

    image generation and translation

    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
     is
    0.44
     shrink
    0.44
    *
    0.44
    負
    0.44
    निर्देश
    0.43
     vag
    0.43
    semantics
    0.42
    رر
    0.42
    ವರಿಗೆ
    0.42
    ール
    0.41
    POSITIVE LOGITS
     peritone
    0.55
     Goethe
    0.52
     GoObject
    0.52
     Lenz
    0.51
    fondo
    0.50
     Allemagne
    0.50
    léans
    0.50
     }{}_{\
    0.50
     ønsker
    0.50
     elementType
    0.49
    Activations Density 0.000%

    No Known Activations