© 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. 164783
    Prev
    Next
    INDEX
    Explanations

    comparing things or options

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

    cookie comparison

    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
     Partly
    0.50
     {:
    0.46
     ;
    0.43
     scramble
    0.43
     torrential
    0.43
     ‘‘
    0.42
     polluted
    0.42
     tarea
    0.42
     entree
    0.42
     peculiar
    0.41
    POSITIVE LOGITS
    ViewModels
    0.54
    куп
    0.52
    EditText
    0.50
     unequivocally
    0.49
    CapsLock
    0.49
    𝑬
    0.49
    hedra
    0.48
     Advocates
    0.47
    чики
    0.46
    ষ্টি
    0.45
    Activations Density 0.002%

    No Known Activations