© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13554
    Prev
    Next
    INDEX
    Explanations

    information or function

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

    logic operations

    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_16k_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
    4
    0.44
    illian
    0.41
    ↵
    0.40
    0
    0.40
    ila
    0.40
    nai
    0.39
    baj
    0.39
    3
    0.39
    2
    0.37
     with
    0.36
    POSITIVE LOGITS
     குறிப்பிட்ட
    0.48
     தச
    0.47
     underpinning
    0.43
    ம்தான்
    0.43
     месту
    0.43
    ですし
    0.42
     између
    0.41
     профессор
    0.41
     sogar
    0.40
    წინ
    0.40
    Activations Density 0.295%

    No Known Activations