© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 9343
    Prev
    Next
    INDEX
    Explanations

    UI elements and question types

    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
    顓
    1.12
    試験
    1.08
     실패
    1.06
     시험
    1.06
    ட்டைகோ
    1.04
     試験
    1.03
     kõige
    1.03
     voordat
    1.03
     사건
    1.00
    失敗
    0.99
    POSITIVE LOGITS
     furniture
    0.87
     person
    0.86
    又要
    0.80
    furniture
    0.79
    arl
    0.77
     grids
    0.77
    又
    0.75
    elm
    0.75
    elae
    0.75
     accordingly
    0.74
    Activations Density 0.218%

    No Known Activations