© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 4133
    Prev
    Next
    INDEX
    Explanations

    Okay, here are ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    镓
    3.01
    이너
    2.79
    แย
    2.70
    狽
    2.69
     д
    2.66
    𝗨
    2.63
    রুখ
    2.63
    োর
    2.63
    />}/>
    2.61
    ⺊
    2.61
    POSITIVE LOGITS
    ếm
    2.66
    箓
    2.52
    deg
    2.40
    atosis
    2.40
    AsUp
    2.39
     Liye
    2.30
    nement
    2.25
    nights
    2.21
    lorescence
    2.21
     ontvang
    2.21
    Activations Density 0.084%

    No Known Activations