© 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. 3751
    Prev
    Next
    INDEX
    Explanations

    math and code abbreviations

    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
    紘
    0.62
     ٿ
    0.61
     Aditya
    0.60
    ួល
    0.59
    adera
    0.58
    莒
    0.57
    teres
    0.57
    Calend
    0.56
    വു
    0.56
    ாள்
    0.55
    POSITIVE LOGITS
    N
    2.06
     N
    1.86
     NS
    1.81
     NN
    1.81
    NC
    1.78
     NP
    1.77
    NN
    1.76
    NP
    1.73
    NR
    1.72
     NC
    1.72
    Activations Density 1.090%

    No Known Activations