© 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. 202697
    Prev
    Next
    INDEX
    Explanations

    mission to help

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

    subjective assessment or search

    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
     Funktionen
    0.54
     Cloth
    0.47
     ფუნქ
    0.47
    즐
    0.46
    ැ
    0.46
    帐
    0.46
     Dining
    0.44
    所有的
    0.43
    있
    0.42
     griech
    0.41
    POSITIVE LOGITS
     말미
    0.49
    น
    0.48
     égard
    0.45
     xgb
    0.44
     affidavits
    0.43
     flog
    0.43
    nay
    0.43
     therefrom
    0.43
    XmlElement
    0.43
     इससे
    0.43
    Activations Density 0.000%

    No Known Activations