© 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. 9372
    Prev
    Next
    INDEX
    Explanations

    data structures and code

    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
    ?;
    1.09
    az
    1.00
    bgcolor
    1.00
    unik
    1.00
     aerobic
    0.99
     mù
    0.99
    gol
    0.98
    bound
    0.97
     essay
    0.97
    []);
    0.96
    POSITIVE LOGITS
     Radeon
    1.19
     против
    1.17
    ших
    1.15
     svojih
    1.12
     لڑ
    1.12
    ROTTLE
    1.12
    стам
    1.10
     Brawl
    1.09
     حول
    1.08
     กว่า
    1.08
    Activations Density 0.000%

    No Known Activations