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. 1103
    Prev
    Next
    INDEX
    Explanations

    words starting with tr

    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
     truth
    1.02
    ೃಹ
    0.95
    ри
    0.94
     disclaimer
    0.94
    ܒ
    0.93
     twin
    0.92
    twin
    0.91
    Trước
    0.89
    thrust
    0.89
    яв
    0.88
    POSITIVE LOGITS
    jillo
    1.23
    iscuit
    1.16
    와이스
    1.14
    FFIC
    1.12
    NSDictionary
    1.11
    あえず
    1.10
    poline
    1.09
     आर्मी
    1.05
    ectoria
    1.03
    ⎡
    1.02
    Activations Density 0.629%

    No Known Activations