© 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. 9269
    Prev
    Next
    INDEX
    Explanations

    any [noun]

    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
    ors
    2.47
    icts
    2.19
    ocols
    2.05
    ⓤ
    2.03
    aterally
    2.03
     Το
    2.01
    ivariable
    1.99
    ICIAL
    1.98
    嵘
    1.98
    enação
    1.98
    POSITIVE LOGITS
    seat
    2.70
    la
    2.68
     outgrowth
    2.68
    cubic
    2.51
    깐
    2.50
    tha
    2.47
    획
    2.44
    mują
    2.30
    ாதை
    2.28
    where
    2.27
    Activations Density 0.234%

    No Known Activations