© 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. 14231
    Prev
    Next
    INDEX
    Explanations

    waves in winter

    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
    า
    1.99
     लागि
    1.94
    াদেশিক
    1.90
    orthogonal
    1.88
    osaur
    1.86
    Lr
    1.86
    armée
    1.86
    🇴
    1.83
    oise
    1.82
    ﾞ
    1.81
    POSITIVE LOGITS
     sati
    1.73
    ुक
    1.62
    اکی
    1.56
    مس
    1.56
    吉祥
    1.51
    rishna
    1.47
     chí
    1.47
     natthi
    1.46
    lasting
    1.45
     ستار
    1.45
    Activations Density 0.009%

    No Known Activations