© 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. 45238
    Prev
    Next
    INDEX
    Explanations

    mailing lists and archives

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

    table schema definitions

    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
    ᆼ
    0.48
    ៩
    0.45
    бое
    0.45
    㽡
    0.45
    РА
    0.44
    РО
    0.44
    umbres
    0.43
    дні
    0.43
    ారా
    0.43
    Mush
    0.43
    POSITIVE LOGITS
     Premier
    0.45
     Make
    0.45
     Ha
    0.43
    :
    0.43
     TJ
    0.42
     Communications
    0.41
    :<
    0.41
     Chart
    0.41
     MP
    0.41
     Express
    0.41
    Activations Density 0.000%

    No Known Activations