© 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. 7-GEMMASCOPE-2-RES-16K
    4. 14384
    Prev
    Next
    INDEX
    Explanations

    math, numbers, sequences

    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
    絬
    2.58
    kaç
    2.50
    zeich
    2.32
    เจ้า
    2.30
    ाइ
    2.28
    rapid
    2.28
     TNFR
    2.22
    epar
    2.22
    ET
    2.21
     випад
    2.20
    POSITIVE LOGITS
    <bos>
    2.78
    стки
    2.01
    tpc
    2.01
    ioutil
    1.93
     걸
    1.91
    hne
    1.87
     urlpatterns
    1.84
    AuthState
    1.83
    تي
    1.82
     없을
    1.80
    Activations Density 0.002%

    No Known Activations