© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8437
    Prev
    Next
    INDEX
    Explanations

    documentation and resource links

    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_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
     cristianos
    0.54
    ﺀ
    0.52
     deportivas
    0.52
     associés
    0.51
    ্জ
    0.50
    льне
    0.49
     delanter
    0.49
     françaises
    0.47
     alrededores
    0.47
     Франции
    0.47
    POSITIVE LOGITS
    U
    0.47
    生活
    0.46
    一
    0.45
    أ
    0.44
     Transformer
    0.44
    會
    0.44
    ur
    0.43
    初
    0.42
    Hed
    0.42
    就
    0.42
    Activations Density 0.010%

    No Known Activations