© 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. 71739
    Prev
    Next
    INDEX
    Explanations

    listed professionals or bathing monkeys

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

    camping book, burning the, nihilism often

    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
    掌
    0.56
    मणि
    0.46
    пів
    0.44
    会儿
    0.44
    舆
    0.43
     Comune
    0.42
     пот
    0.42
    ೊಂದು
    0.42
     RECEIVED
    0.41
    िम
    0.41
    POSITIVE LOGITS
    fract
    0.50
     extrapolated
    0.47
    archivo
    0.46
    дов
    0.45
     extrapol
    0.45
    ListView
    0.45
    ře
    0.44
     vinc
    0.44
    jem
    0.44
    擠
    0.44
    Activations Density 0.000%

    No Known Activations