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. 7329
    Prev
    Next
    INDEX
    Explanations

    noun followed by is

    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
    sam
    0.73
    ところ
    0.70
    다
    0.68
     infamous
    0.67
     وتع
    0.66
     demikian
    0.66
     their
    0.65
    ил
    0.64
    هن
    0.63
     The
    0.62
    POSITIVE LOGITS
    번호
    0.91
     dioxide
    0.89
     χωρίς
    0.83
     MOQ
    0.83
    𝟏
    0.81
    ového
    0.81
    𝑦
    0.78
     drawable
    0.78
    嘅
    0.78
     యొక్క
    0.78
    Activations Density 4.304%

    No Known Activations