© 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. 4099
    Prev
    Next
    INDEX
    Explanations

    motivation, Nazism, engine options

    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
    Hold
    2.54
    íu
    2.30
    র্ষ
    2.10
    퍽
    2.08
    ০০
    2.07
    বীন্দ্র
    2.01
     flare
    2.01
     נפ
    1.99
    ెంట్
    1.97
    ্টর
    1.91
    POSITIVE LOGITS
     HttpStatus
    3.35
    obacterial
    2.97
     celui
    2.90
    兘
    2.90
     TabLayout
    2.76
     attaques
    2.74
     Yn
    2.72
    圿
    2.71
    ادر
    2.70
    ric
    2.67
    Activations Density 0.373%

    No Known Activations