Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 3482
    Prev
    Next
    INDEX
    Explanations

    explanation

    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
    :<
    1.37
    :...
    1.36
     reliefs
    1.32
    :*
    1.32
     overlays
    1.30
    ρια
    1.29
    :“
    1.27
    :&
    1.27
     repeal
    1.27
    :</
    1.26
    POSITIVE LOGITS
    ↵↵
    1.33
     Namun
    1.10
    ↵
    1.10
     Isid
    1.04
    Walking
    1.01
     However
    1.00
    sac
    0.99
     Wochschr
    0.98
    However
    0.98
     Hacienda
    0.97
    Activations Density 0.001%

    No Known Activations