© 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. 17-GEMMASCOPE-2-RES-16K
    7. 187
    Prev
    Next
    INDEX
    Explanations

    .org and .com URLs

    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_17_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
    ဵ
    0.47
    barer
    0.45
    ousing
    0.43
    shifting
    0.43
    winding
    0.43
    ostomy
    0.43
     mobility
    0.42
    arynx
    0.41
    ំព
    0.41
    rightbar
    0.40
    POSITIVE LOGITS
     reciente
    0.50
    کے
    0.49
    Maria
    0.48
     recente
    0.47
    ی
    0.47
    ドイツ
    0.47
     Tidak
    0.46
    How
    0.46
     tidak
    0.46
    で
    0.45
    Activations Density 0.897%

    No Known Activations