© 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. 2866
    Prev
    Next
    INDEX
    Explanations

    every other

    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
     gj
    2.13
     carry
    2.06
    뮈
    2.01
    های
    1.92
    늉
    1.92
     kontakt
    1.85
     anf
    1.81
    흡
    1.80
    뻑
    1.78
    는다
    1.72
    POSITIVE LOGITS
    ly
    1.93
    valent
    1.89
    érapie
    1.85
    ibre
    1.85
    waiting
    1.83
    theme
    1.81
    nuclear
    1.80
    uña
    1.78
    rd
    1.76
    monium
    1.75
    Activations Density 0.006%

    No Known Activations