© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3257
    Prev
    Next
    INDEX
    Explanations

    often challenging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tro
    1.13
     Tom
    0.95
     Тре
    0.93
     Tri
    0.92
     TB
    0.90
     Τ
    0.90
     Taz
    0.88
     Три
    0.88
     тре
    0.87
    Tas
    0.87
    POSITIVE LOGITS
     Harwell
    0.78
     Mule
    0.78
    <unused2122>
    0.75
     JavaBeans
    0.72
     Caff
    0.71
    ভোকেট
    0.71
     Humber
    0.69
    ^{-
    0.68
    <0xB4>
    0.68
     caffè
    0.68
    Activations Density 1.615%

    No Known Activations