Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7276
    Prev
    Next
    INDEX
    Explanations

    NP complexity problems

    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_9_width_262k_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
    en
    1.51
    %.
    1.45
    ostics
    1.44
     epsilon
    1.41
     unsound
    1.40
     astute
    1.40
    体积
    1.38
    ㎥
    1.38
     struts
    1.35
     '#'
    1.35
    POSITIVE LOGITS
    д
    1.88
    ்
    1.72
    ाइन
    1.71
    И
    1.62
    ب
    1.46
    л
    1.43
    ্ব
    1.41
     Mesmo
    1.36
    ्सा
    1.34
     siano
    1.33
    Activations Density 0.008%

    No Known Activations