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. 7305
    Prev
    Next
    INDEX
    Explanations

    mathematical notation Z

    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
    و
    2.55
    ل
    2.32
    as
    2.14
    그
    1.97
    на
    1.93
    am
    1.93
    s
    1.82
    től
    1.77
    Alla
    1.72
    sylvania
    1.71
    POSITIVE LOGITS
     дает
    1.84
     Terbaru
    1.84
     Wikiseite
    1.78
    မဲ့
    1.68
    󠁳
    1.68
     отмеча
    1.64
    તમાં
    1.64
     mobilized
    1.63
     μαζί
    1.63
    ła
    1.62
    Activations Density 0.001%

    No Known Activations