© 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. 10486
    Prev
    Next
    INDEX
    Explanations

    lake and recreation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     shaking
    2.88
     compulsive
    2.82
     briefing
    2.77
    ্ড
    2.76
     shoving
    2.74
    ্ঠ
    2.72
    
    2.70
    琲
    2.69
     thumbs
    2.67
    ↥
    2.65
    POSITIVE LOGITS
    ing
    3.44
    ی
    3.41
    <bos>
    2.92
    amt
    2.70
    ombo
    2.40
    yth
    2.39
    た
    2.36
    Alpes
    2.34
    هن
    2.32
     veliko
    2.30
    Activations Density 0.023%

    No Known Activations