© 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. 48
    Prev
    Next
    INDEX
    Explanations

    going through, get to

    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
    opolitan
    0.97
    Collapse
    0.87
    ྐ
    0.87
    anthem
    0.87
    ise
    0.87
    шка
    0.87
    income
    0.86
     completes
    0.85
    accus
    0.85
    ist
    0.84
    POSITIVE LOGITS
    𝘳
    1.22
     lucr
    1.02
    aways
    0.99
    рость
    0.97
    reten
    0.95
    ینګ
    0.93
    рати
    0.91
    ္ဂ
    0.89
    ActivityCompat
    0.89
     balanceOf
    0.88
    Activations Density 3.437%

    No Known Activations