© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 10682
    Prev
    Next
    INDEX
    Explanations

    calculating using equations and formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     উপায়
    0.85
     활용
    0.82
    প
    0.79
     Hälfte
    0.79
     recommandée
    0.77
     stints
    0.76
     Schritte
    0.76
     खासदार
    0.75
     pformat
    0.75
     Wege
    0.74
    POSITIVE LOGITS
    unlike
    0.86
    𝗍
    0.78
    tens
    0.75
     hacemos
    0.74
    థ
    0.74
    भारतीय
    0.74
    ఇ
    0.74
    ẫu
    0.74
    generally
    0.73
    لاش
    0.73
    Activations Density 0.004%

    No Known Activations