© 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. 246435
    Prev
    Next
    INDEX
    Explanations

    more, research, begin, sheet

    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
    I
    0.55
     paradigms
    0.52
    n
    0.51
    8
    0.51
    KPI
    0.49
    0
    0.47
     mammal
    0.47
     compassion
    0.46
     diagrams
    0.46
    CONNECTED
    0.45
    POSITIVE LOGITS
     Rather
    0.53
     ዘዴ
    0.51
     Pren
    0.48
    ధిక
    0.48
     Shrine
    0.47
    惮
    0.47
     የመጀመሪያ
    0.46
     Battlefield
    0.46
     الداله
    0.46
     Verona
    0.46
    Activations Density 0.002%

    No Known Activations