© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14233
    Prev
    Next
    INDEX
    Explanations

    app descriptions following "App:"

    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_7_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
    pun
    1.88
     seguito
    1.80
    gggg
    1.79
    mail
    1.77
    ूंकि
    1.75
    (\
    1.74
    ậu
    1.71
    ..--
    1.70
    昌
    1.69
    }(\
    1.69
    POSITIVE LOGITS
    plicial
    2.64
     preferences
    2.51
     codified
    2.13
     canoe
    2.12
     preference
    2.08
     canoes
    2.04
    鳅
    2.01
     optimal
    2.00
     addons
    1.97
     hips
    1.96
    Activations Density 0.075%

    No Known Activations