© 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. 52145
    Prev
    Next
    INDEX
    Explanations

    showbusiness, Court outcomes, deadlines

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

    used for confirmation

    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
     Enabled
    0.54
     Paddle
    0.54
     Metals
    0.54
     Aid
    0.53
     Heraus
    0.53
     Exploring
    0.52
     Experiment
    0.52
    糍
    0.52
     Cry
    0.51
     Visualization
    0.51
    POSITIVE LOGITS
    輸入品
    0.53
    receipt
    0.50
    stre
    0.50
    transactions
    0.49
    heli
    0.48
    носить
    0.48
    vais
    0.48
    reno
    0.48
    opin
    0.48
    ad
    0.47
    Activations Density 0.000%

    No Known Activations