© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6904
    Prev
    Next
    INDEX
    Explanations

    "you always..." accusations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     ktorí
    1.35
    Utf
    1.31
    ával
    1.30
     contratación
    1.29
     indiquant
    1.28
     kteří
    1.27
     tierras
    1.27
    ޘ
    1.27
     gördüğünüz
    1.26
    niają
    1.25
    POSITIVE LOGITS
     ар
    0.83
     OK
    0.79
    hik
    0.77
     progressively
    0.75
     ID
    0.74
     estimation
    0.74
     okay
    0.74
     核
    0.72
     Vard
    0.72
     NUMBER
    0.71
    Activations Density 0.251%

    No Known Activations