Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 77
    Prev
    Next
    INDEX
    Explanations

    not necessarily

    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_16_width_16k_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
     I
    0.85
     O
    0.75
     
    0.73
    a
    0.73
     itineraries
    0.70
     binoculars
    0.68
     L
    0.67
     formats
    0.64
     workloads
    0.63
    ード
    0.63
    POSITIVE LOGITS
    t
    1.02
    л
    1.01
     on
    0.86
    ası
    0.86
    ۹
    0.84
    д
    0.84
    ح
    0.77
    ۱
    0.75
    direccion
    0.73
    ار
    0.73
    Activations Density 0.802%

    No Known Activations