© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3177
    Prev
    Next
    INDEX
    Explanations

    educational or illustrative purposes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_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
     aggressiveness
    0.87
     노력
    0.82
     entusiasmo
    0.82
    reements
    0.82
    ដែល
    0.80
    સર
    0.79
     attitudes
    0.78
    祝
    0.78
    ్ఞ
    0.78
     Attitudes
    0.77
    POSITIVE LOGITS
     purposes
    2.36
     purpose
    2.03
     Purposes
    1.87
     sake
    1.86
     Purpose
    1.69
    purpose
    1.58
    Purpose
    1.53
     PURPOSE
    1.28
     Sake
    1.22
     propósito
    1.14
    Activations Density 0.147%

    No Known Activations