© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13503
    Prev
    Next
    INDEX
    Explanations

    comparisons using than

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

    comparisons using than

    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_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
     sieve
    0.43
     sk
    0.40
     slim
    0.39
    筛
    0.39
     compress
    0.39
     arg
    0.39
     insign
    0.38
    ()<
    0.38
     cal
    0.38
     corrector
    0.38
    POSITIVE LOGITS
     Estamos
    0.55
     Иң
    0.47
    䊂
    0.47
    Estamos
    0.46
    洶
    0.45
    Tmp
    0.45
    efeller
    0.45
    Lad
    0.45
    <unused1766>
    0.44
    उचर
    0.44
    Activations Density 0.003%

    No Known Activations