© 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. 2810
    Prev
    Next
    INDEX
    Explanations

    sensory input and experience

    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
    sters
    3.02
    رځ
    2.93
    رخ
    2.79
    las
    2.72
    ﺑ
    2.70
    ر
    2.59
    luoromethyl
    2.53
     αι
    2.46
    smoked
    2.45
    do
    2.43
    POSITIVE LOGITS
    திகளை
    2.60
    ething
    2.47
    ഷ്‌
    2.34
    ์
    2.30
    திகள்
    2.28
    惮
    2.27
    имо
    2.27
    anha
    2.26
     upt
    2.24
     BorderRadius
    2.24
    Activations Density 0.164%

    No Known Activations