© 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. 11687
    Prev
    Next
    INDEX
    Explanations

    to go, need specific, level represents

    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
     Exercise
    0.52
     Effects
    0.48
    т
    0.47
    व
    0.47
     Hunger
    0.46
     Remarks
    0.46
    Exercise
    0.46
     Favorite
    0.46
     Mature
    0.46
     Exercises
    0.46
    POSITIVE LOGITS
    ojana
    0.61
     regol
    0.55
    elesaikan
    0.52
     shayari
    0.51
     ቦ
    0.51
    ଥି
    0.49
    azał
    0.49
    rifle
    0.48
    asaan
    0.48
     قاعد
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.