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. 7352
    Prev
    Next
    INDEX
    Explanations

    working from home

    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
    که
    1.45
     clot
    1.45
     precaution
    1.41
    嘿
    1.40
     cloudy
    1.37
     shoots
    1.36
    нт
    1.36
    ৮
    1.34
     yearling
    1.33
    cope
    1.33
    POSITIVE LOGITS
    entityManager
    1.51
     Considerable
    1.49
    ers
    1.42
    お得
    1.38
     안
    1.36
    я
    1.35
    म
    1.34
     entityManager
    1.33
    وون
    1.30
     iria
    1.30
    Activations Density 0.000%

    No Known Activations