© 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. 209402
    Prev
    Next
    INDEX
    Explanations

    place names or specific brands

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

    phrases like "up to" or "could have"

    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
    "
    0.65
     lapses
    0.53
    "<
    0.51
    u
    0.50
    "/"
    0.47
    "\
    0.46
    "".
    0.46
    bido
    0.46
    ">'
    0.46
    Moscow
    0.46
    POSITIVE LOGITS
    에
    0.47
     cardinal
    0.46
    ছনে
    0.44
    ன்
    0.44
     của
    0.43
     ३
    0.43
     hãng
    0.43
     hustle
    0.43
     myeloid
    0.42
     bas
    0.42
    Activations Density 0.000%

    No Known Activations