© 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. 74125
    Prev
    Next
    INDEX
    Explanations

    possess, wish, obtain, everyone

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

    limiting advice or making disclaimers

    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
    czę
    0.47
     ഹോ
    0.44
     regelmatig
    0.43
     Hispanics
    0.42
     generalizes
    0.42
     nghiên
    0.41
    +//
    0.41
     getLast
    0.41
     выгод
    0.41
    有助于
    0.41
    POSITIVE LOGITS
    entiti
    0.48
    त्न
    0.47
    osx
    0.45
    켰
    0.44
     rangi
    0.44
    jd
    0.44
    JB
    0.44
    딜
    0.43
    accus
    0.43
    뵐
    0.43
    Activations Density 0.002%

    No Known Activations