© 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. 233224
    Prev
    Next
    INDEX
    Explanations

    things like, trends appear, shall be

    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
     Soda
    0.52
     Sodium
    0.46
     Soa
    0.46
     Enable
    0.46
    ﺶ
    0.46
     Telephone
    0.45
     Supply
    0.45
     Discrete
    0.45
    ⺝
    0.45
     Elke
    0.45
    POSITIVE LOGITS
     sisters
    0.48
     ${(
    0.48
     turnips
    0.46
    appreciated
    0.45
    airo
    0.45
     coup
    0.44
     budding
    0.43
    herst
    0.42
    oks
    0.42
     pausing
    0.41
    Activations Density 0.001%

    No Known Activations