© 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. 17-GEMMASCOPE-2-RES-16K
    7. 455
    Prev
    Next
    INDEX
    Explanations

    .com/

    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_17_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
     said
    0.77
     possible
    0.77
     in
    0.76
     getters
    0.73
     /
    0.72
     values
    0.70
     with
    0.70
     correctness
    0.67
     halt
    0.67
     needs
    0.65
    POSITIVE LOGITS
    #!
    1.43
    #.
    1.36
    popup
    1.26
    +%
    1.25
    _%
    1.24
    lightbox
    1.24
    #
    1.22
    &&
    1.21
    StoreID
    1.20
    widget
    1.18
    Activations Density 0.535%

    No Known Activations