© 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. 115315
    Prev
    Next
    INDEX
    Explanations

    know is / needs

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

    individuals, man, B

    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
     =
    0.48
    ấp
    0.45
     cake
    0.44
     မိ
    0.43
     bild
    0.43
    sville
    0.42
    iform
    0.42
    ,
    0.41
    cake
    0.41
     Cake
    0.41
    POSITIVE LOGITS
    ÉR
    0.50
    ム
    0.50
     RETURNS
    0.50
    TEAM
    0.49
    FRAMERATE
    0.48
     Omphalodes
    0.48
    PERATURE
    0.48
     সরানো
    0.47
     அரங்க
    0.47
     MONITOR
    0.47
    Activations Density 0.001%

    No Known Activations