© 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. 238907
    Prev
    Next
    INDEX
    Explanations

    report and prior information

    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
    ammonium
    0.53
    suppliers
    0.48
     puris
    0.48
    Mitsubishi
    0.48
    dess
    0.47
    ז
    0.46
    з
    0.46
    hanger
    0.45
    MovieModal
    0.44
    childComplexity
    0.44
    POSITIVE LOGITS
     earlier
    0.52
    報告
    0.51
     UE
    0.50
    原始
    0.47
    昨年
    0.47
     ON
    0.47
     witness
    0.47
     report
    0.46
    召
    0.46
     prior
    0.46
    Activations Density 0.000%

    No Known Activations