© 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. 55924
    Prev
    Next
    INDEX
    Explanations

    appearance, color, and texture

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

    flavor and nuance descriptors

    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
     verwenden
    0.52
    ocl
    0.44
     повіт
    0.42
    
    0.42
     লিমি
    0.42
     möglicherweise
    0.41
     hoặc
    0.41
    Qualified
    0.41
    របស់យើង
    0.40
    stitches
    0.40
    POSITIVE LOGITS
     superbly
    0.52
     correcta
    0.48
     beautifully
    0.47
    ]==
    0.46
    賏
    0.46
    ياته
    0.46
     nicely
    0.46
     tutti
    0.45
     deftly
    0.44
     maar
    0.44
    Activations Density 0.015%

    No Known Activations