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. 22-GEMMASCOPE-2-RES-16K
    4. 9809
    Prev
    Next
    INDEX
    Explanations

    two offices

    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_22_width_16k_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
     Fujita
    1.08
    ปัญหา
    0.98
     שלא
    0.96
    astrous
    0.96
    ও
    0.95
     legitimacy
    0.95
    aneous
    0.93
    সই
    0.92
    Source
    0.89
    Identifier
    0.88
    POSITIVE LOGITS
     arme
    1.01
     insect
    0.99
    es
    0.95
    mataspid
    0.94
    рт
    0.93
    ném
    0.92
    دست
    0.92
    <unused2139>
    0.91
    iere
    0.91
    ería
    0.91
    Activations Density 0.005%

    No Known Activations