© 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. 2802
    Prev
    Next
    INDEX
    Explanations

    numerical ranges and versions

    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
    ικών
    1.68
    
    1.65
    োর্টের
    1.63
    liste
    1.57
    avni
    1.56
    cnpj
    1.54
    Marco
    1.54
    marco
    1.52
     counterclaim
    1.52
    ListItemIcon
    1.49
    POSITIVE LOGITS
     reasons
    1.78
    <bos>
    1.77
     reason
    1.67
    y
    1.43
     purposes
    1.38
     why
    1.36
     host
    1.35
     detained
    1.30
     Esto
    1.30
     Reasons
    1.29
    Activations Density 0.338%

    No Known Activations