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. 29-GEMMASCOPE-2-RES-262K
    4. 505
    Prev
    Next
    INDEX
    Explanations

    have recently done

    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_29_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
    DBOutput
    0.78
    平台
    0.72
    平台的
    0.65
    <unused2049>
    0.65
    <unused452>
    0.65
    뭣
    0.64
    莨
    0.64
    平台上
    0.64
    根
    0.63
    проце
    0.63
    POSITIVE LOGITS
     increased
    1.00
     recently
    0.94
    Increased
    0.94
     now
    0.93
     succesfully
    0.93
     obecnie
    0.91
     actualmente
    0.91
    increased
    0.91
     currently
    0.91
     decided
    0.90
    Activations Density 0.036%

    No Known Activations