© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6758
    Prev
    Next
    INDEX
    Explanations

    be very clear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     switchTo
    0.94
     conceit
    0.92
    បន្ថែម
    0.91
    ୍କ
    0.91
    attham
    0.87
    ंख्य
    0.87
    쨔
    0.87
    besiege
    0.87
    蹰
    0.84
    atifs
    0.84
    POSITIVE LOGITS
     clear
    0.84
     White
    0.79
     Clear
    0.77
    Clear
    0.68
     white
    0.68
     CLEAR
    0.62
    clear
    0.61
    White
    0.60
     perfectly
    0.58
     Orange
    0.56
    Activations Density 0.050%

    No Known Activations