© 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. 53516
    Prev
    Next
    INDEX
    Explanations

    Should this

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

    probability distribution

    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
    攙
    0.51
     спа
    0.50
    蓦
    0.50
    archiwizowane
    0.50
    ǎng
    0.49
    也不能
    0.49
     ग्रेजुएशन
    0.49
     anciens
    0.47
     empêcher
    0.47
    ⒏
    0.46
    POSITIVE LOGITS
    ↵↵
    0.55
     tert
    0.50
     monthly
    0.48
     this
    0.47
     quarterly
    0.47
     tidy
    0.47
    -
    0.45
     Two
    0.45
     NOT
    0.44
    fire
    0.44
    Activations Density 0.000%

    No Known Activations