© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3109
    Prev
    Next
    INDEX
    Explanations

    step by step thinking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     ب
    1.37
     م
    1.35
     لم
    1.32
     ک
    1.28
     وح
    1.20
     ن
    1.20
     إ
    1.20
     ス
    1.19
     अ
    1.17
     न
    1.16
    POSITIVE LOGITS
     etc
    0.79
    /
    0.69
     or
    0.62
     প্রক্রিয়াধীন
    0.59
     act
    0.55
     thereof
    0.52
    ()}.
    0.48
    act
    0.47
     real
    0.47
    ).
    0.46
    Activations Density 2.152%

    No Known Activations