© 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. 112625
    Prev
    Next
    INDEX
    Explanations

    best serve, bold new

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

    guess my emotions

    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
    B
    0.56
    farm
    0.54
    Ej
    0.54
    ut
    0.53
    ES
    0.53
    cut
    0.52
    Ber
    0.52
    S
    0.52
    last
    0.51
    may
    0.51
    POSITIVE LOGITS
     пан
    0.54
     случаях
    0.52
     চির
    0.51
     দলীয়
    0.51
     hama
    0.50
     вино
    0.50
     кален
    0.50
     컬러
    0.50
     мали
    0.49
     Вале
    0.47
    Activations Density 0.000%

    No Known Activations