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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 303
    Prev
    Next
    INDEX
    Explanations

    how to construct

    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
    a
    1.34
    at
    1.32
    ag
    1.31
    o
    1.26
    ar
    1.26
    usb
    1.25
    i
    1.22
    .
    1.21
    as
    1.21
    us
    1.19
    POSITIVE LOGITS
     insanlar
    1.95
     mensen
    1.84
     they
    1.78
     these
    1.76
     ljudi
    1.75
     insanların
    1.74
     THEY
    1.71
     everyone
    1.68
     everybody
    1.66
     oamenii
    1.66
    Activations Density 4.662%

    No Known Activations