© 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. 21068
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives, prices

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

    roman numerals and numbers with units

    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
    bart
    0.53
    bytes
    0.51
    aises
    0.48
    <0xC2>
    0.46
    ies
    0.46
    zada
    0.46
    axes
    0.46
    btnClose
    0.46
    ,“
    0.45
    POSITIVE LOGITS
    -}\
    0.48
     Sehr
    0.47
    סט
    0.47
    弱
    0.47
    渚
    0.46
    陷入
    0.46
    нды
    0.46
     그렇게
    0.45
    溲
    0.45
     Bigger
    0.45
    Activations Density 0.000%

    No Known Activations