© 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. 352
    Prev
    Next
    INDEX
    Explanations

    specific problems and steps

    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
     is
    1.22
     a
    1.21
     не
    1.13
     to
    1.12
     and
    1.12
     It
    1.11
    .
    1.09
     in
    1.09
     with
    1.08
     has
    1.08
    POSITIVE LOGITS
     intricacies
    1.11
     interplay
    1.09
     shortcomings
    1.04
     vattum
    1.02
    localVarPath
    1.02
     potentialities
    0.99
     impending
    0.98
     viciss
    0.97
     myriad
    0.97
     hardships
    0.97
    Activations Density 3.398%

    No Known Activations