© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 142451
    Prev
    Next
    INDEX
    Explanations

    and somewhat; and more

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

    discipline and monitoring

    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
    Not in Any Lists

    No Comments

    Negative Logits
     እንቅ
    0.48
    likelihood
    0.43
     incidences
    0.42
    ә
    0.40
    룰
    0.39
     뒷
    0.39
    lack
    0.39
    恩
    0.39
    determining
    0.38
    ถ
    0.38
    POSITIVE LOGITS
     zajedno
    0.48
     mobilize
    0.46
     revolutionize
    0.46
     Shib
    0.44
     appass
    0.44
     prescribe
    0.43
     yardımcı
    0.43
     ingeniería
    0.43
    islav
    0.43
    坩
    0.42
    Activations Density 0.005%

    No Known Activations