© 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. 3859
    Prev
    Next
    INDEX
    Explanations

    musical theater performances

    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
    ي
    3.33
    ル
    2.78
    िलो
    2.46
    িস্থ
    2.26
    Riemann
    2.19
     adhering
    2.18
    nå
    2.17
    heur
    2.17
    ENC
    2.15
     hoạch
    2.11
    POSITIVE LOGITS
    tre
    2.21
    zené
    2.13
    preneurs
    2.05
    𝘳
    2.04
    ight
    2.03
    𝘩
    2.02
    ates
    1.97
    aling
    1.95
    fters
    1.95
    theon
    1.94
    Activations Density 0.023%

    No Known Activations