© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63563
    Prev
    Next
    INDEX
    Explanations

    stadium environments

    np_acts-logits-general · gemini-2.5-flash-lite

    subterranean river, hidden cameras, local meetings, children, problem statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    securityMarks
    0.48
    rtel
    0.46
    ρού
    0.46
    ackbar
    0.46
    webhook
    0.45
    𝐈
    0.45
    าท
    0.44
    fix
    0.44
     ume
    0.44
     fondateur
    0.43
    POSITIVE LOGITS
    लाई
    0.49
     shirts
    0.48
    ğinin
    0.42
    żenia
    0.42
    MOND
    0.41
     ||=
    0.41
     annivers
    0.40
     nessuna
    0.40
    也是
    0.40
    表明
    0.39
    Activations Density 0.000%

    No Known Activations