© 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. 51201
    Prev
    Next
    INDEX
    Explanations

    east facing, insufficiently active

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

    binary logic operations

    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
     정확
    0.51
     בל
    0.50
    ברו
    0.50
     작은
    0.50
    jera
    0.48
     を
    0.47
     चम्म
    0.47
     옵
    0.46
     верши
    0.46
     정보를
    0.46
    POSITIVE LOGITS
     Bharat
    0.48
     hookah
    0.48
    可通过
    0.46
     $\
    0.46
     discourse
    0.46
     adduct
    0.46
     asthma
    0.45
     Air
    0.45
     exposure
    0.45
     disparities
    0.44
    Activations Density 0.000%

    No Known Activations