© 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. 26591
    Prev
    Next
    INDEX
    Explanations

    building and defining structures

    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
    }_{-}\
    0.54
     suelen
    0.44
     unint
    0.43
    ются
    0.42
     dvou
    0.42
    ینگ
    0.42
    cious
    0.42
     pudi
    0.41
    atamente
    0.41
    ढ़ाई
    0.41
    POSITIVE LOGITS
    redi
    0.49
     Fees
    0.46
    Fees
    0.45
     中心
    0.43
    ဘ
    0.42
    តា
    0.41
    okra
    0.41
     Martina
    0.40
    venus
    0.40
    中心
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.