© 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. 211027
    Prev
    Next
    INDEX
    Explanations

    making mistakes

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

    functional concepts and utilities

    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
     dienen
    0.46
     olim
    0.46
     (
    0.45
    forderungen
    0.45
    for
    0.45
     فعال
    0.43
    Crypto
    0.43
     Theoret
    0.43
    OGLE
    0.42
    xcsche
    0.42
    POSITIVE LOGITS
     टू
    0.42
     convenient
    0.41
     कॉन्
    0.41
    फना
    0.40
    盻
    0.40
    neys
    0.40
     फ्रेंड्स
    0.40
    atching
    0.40
    손
    0.40
    セ
    0.39
    Activations Density 0.000%

    No Known Activations