© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1122
    Prev
    Next
    INDEX
    Explanations

    phrases starting with what

    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
    Insets
    1.52
    ّل
    1.48
    avacanam
    1.47
    weile
    1.43
    uft
    1.42
    hitva
    1.40
    ت
    1.39
    هه
    1.38
    rename
    1.38
    eee
    1.35
    POSITIVE LOGITS
    देशीर
    1.53
     happens
    1.49
    Copper
    1.48
     acontece
    1.43
     मुख्यमंत्री
    1.43
     δή
    1.38
     ocorre
    1.36
     cobre
    1.35
    follows
    1.34
     Copper
    1.33
    Activations Density 0.412%

    No Known Activations