© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 726
    Prev
    Next
    INDEX
    Explanations

    city is capital

    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
     :).
    1.59
     evitando
    1.41
     ибо
    1.41
    ;.
    1.38
    ۔
    1.37
    :.
    1.37
    ക്കിയത്
    1.36
     żeby
    1.32
     walaupun
    1.32
     :/
    1.31
    POSITIVE LOGITS
     has
    2.68
     will
    2.42
     could
    2.40
     comprises
    2.38
     represents
    2.31
     may
    2.30
    氏は
    2.29
     is
    2.28
     incorporates
    2.28
    도는
    2.25
    Activations Density 3.913%

    No Known Activations