© 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. 247155
    Prev
    Next
    INDEX
    Explanations

    specific words and phrases

    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
     LOFT
    0.55
    보
    0.54
    亏
    0.47
    糟
    0.47
     slowmotion
    0.46
     bellows
    0.45
     booting
    0.45
    斯拉
    0.44
    우
    0.44
     frescos
    0.44
    POSITIVE LOGITS
    uer
    0.59
    itic
    0.57
    nej
    0.55
    hatti
    0.54
    liefer
    0.53
    itlement
    0.52
    lig
    0.51
    itik
    0.50
    enn
    0.50
    rio
    0.50
    Activations Density 0.002%

    No Known Activations