© 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. 22697
    Prev
    Next
    INDEX
    Explanations

    numbers and dimensions

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

    years of experience

    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
    骢
    0.50
     infrastrukt
    0.49
    辂
    0.47
     váy
    0.47
     perg
    0.46
     biber
    0.46
     ủng
    0.46
     différences
    0.46
     opus
    0.45
     phát
    0.45
    POSITIVE LOGITS
    t
    0.63
    an
    0.58
    D
    0.52
    "
    0.50
    C
    0.50
    O
    0.50
    ?
    0.49
    em
    0.49
    F
    0.49
    B
    0.49
    Activations Density 0.023%

    No Known Activations