© 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. 150222
    Prev
    Next
    INDEX
    Explanations

    specific conditions and times

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

    your city

    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
     Kroger
    0.48
    urence
    0.48
     berper
    0.45
     protegido
    0.45
     asing
    0.43
     meni
    0.42
     jde
    0.42
     身
    0.42
     doctor
    0.41
     sodium
    0.41
    POSITIVE LOGITS
     Bulld
    0.50
     Constraints
    0.49
     моде
    0.48
    ཋ
    0.47
    탤
    0.47
    нг
    0.46
     плюс
    0.46
     нати
    0.46
    Фе
    0.46
    hdad
    0.45
    Activations Density 0.001%

    No Known Activations