© 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. 2494
    Prev
    Next
    INDEX
    Explanations

    Unreal Engine 5.3

    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
     DJ
    1.11
    蘇
    1.06
     CT
    0.99
    贖
    0.97
     eun
    0.93
     concl
    0.92
    苏
    0.91
     DZ
    0.90
     COR
    0.90
    corrected
    0.89
    POSITIVE LOGITS
    Having
    1.64
    Historically
    1.42
    When
    1.41
    Looking
    1.41
     Existem
    1.40
    Speaking
    1.40
    Factors
    1.40
    Regarding
    1.40
    Selain
    1.39
    Não
    1.39
    Activations Density 0.068%

    No Known Activations