© 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. 27424
    Prev
    Next
    INDEX
    Explanations

    size and quantity

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

    communication platforms

    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
    行星
    0.51
    Пре
    0.50
    비를
    0.50
    
    0.49
    ffi
    0.48
    prés
    0.47
    Под
    0.47
     catar
    0.46
    нке
    0.46
    тар
    0.46
    POSITIVE LOGITS
     homebuyers
    0.49
     drinker
    0.49
     size
    0.49
     <?
    0.49
     stam
    0.48
     Marin
    0.48
     stem
    0.48
     largest
    0.47
     measurement
    0.47
     nth
    0.47
    Activations Density 0.000%

    No Known Activations