© 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. 52320
    Prev
    Next
    INDEX
    Explanations

    may help

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

    feeling and abstract concepts like facts

    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
    San
    0.51
    i
    0.48
     Blvd
    0.47
    estar
    0.46
    u
    0.46
    Iss
    0.46
    Left
    0.46
    明星
    0.46
     BFF
    0.46
     has
    0.45
    POSITIVE LOGITS
     resignation
    0.49
     тогда
    0.49
     ።
    0.48
     derivations
    0.45
     dlatego
    0.44
     różnych
    0.44
     resign
    0.43
     βοη
    0.43
     daugiau
    0.43
     разных
    0.42
    Activations Density 0.000%

    No Known Activations