© 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. 110518
    Prev
    Next
    INDEX
    Explanations

    I have bookmarked

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

    validation/sanitization and connection

    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
    엽
    0.46
    papa
    0.42
    점에서
    0.42
    意的
    0.42
    žený
    0.41
    чена
    0.41
     ಬಗ್ಗೆ
    0.41
    ଢ
    0.40
    Ь
    0.40
    вед
    0.40
    POSITIVE LOGITS
                
    0.54
     Combs
    0.52
     Thoreau
    0.51
     Infrared
    0.49
     Himalayas
    0.48
     Wrangler
    0.48
     Kabul
    0.47
     parametr
    0.47
     algae
    0.47
     Prag
    0.47
    Activations Density 0.000%

    No Known Activations