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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12078
    Prev
    Next
    INDEX
    Explanations

    C++ output statements

    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_13_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
     trial
    0.96
    屯
    0.91
     Trial
    0.81
     allev
    0.80
     पन
    0.79
     Prote
    0.78
     SEND
    0.78
     Camp
    0.78
     माजी
    0.77
     قوات
    0.77
    POSITIVE LOGITS
     coils
    0.96
    eking
    0.91
    েনের
    0.87
    प्ताहिक
    0.87
     isos
    0.87
    ের
    0.85
    環
    0.84
    环
    0.83
     discloses
    0.82
     GCBO
    0.81
    Activations Density 0.060%

    No Known Activations