© 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. 47447
    Prev
    Next
    INDEX
    Explanations

    posting agreements or terms

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

    discussing specific items after a concept

    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
     কবিতার
    0.43
    や
    0.42
     እና
    0.41
     आणि
    0.41
     ও
    0.41
     અને
    0.39
     Льво
    0.39
     ఒకటి
    0.39
    ም
    0.39
     લા
    0.38
    POSITIVE LOGITS
    之後
    0.44
     renamed
    0.43
     synapse
    0.43
     biopic
    0.43
     senere
    0.41
    libexec
    0.40
     internship
    0.40
     rename
    0.40
     plays
    0.40
     afterlife
    0.39
    Activations Density 0.002%

    No Known Activations