© 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. 3799
    Prev
    Next
    INDEX
    Explanations

    inviting or invitation

    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
    𝓵
    2.48
    𝙾
    2.46
    ⊰
    2.38
     αξ
    2.35
    𝚊
    2.32
     ed
    2.31
     REPORT
    2.30
    𝙰
    2.26
    cle
    2.26
     olt
    2.23
    POSITIVE LOGITS
    م
    3.11
    iejsc
    2.75
    el
    2.67
    streetmap
    2.62
    yaw
    2.55
    y
    2.50
    irtual
    2.49
    ประชุม
    2.49
    雰囲
    2.46
    köz
    2.40
    Activations Density 0.091%

    No Known Activations