© 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. 173020
    Prev
    Next
    INDEX
    Explanations

    that followed by common English words

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

    conditional or non-essential descriptions

    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
     extermin
    0.42
     `
    0.39
    ologist
    0.39
     ஸ்த
    0.39
    坐在
    0.38
    gente
    0.38
     दस्तक
    0.38
     treason
    0.37
    在
    0.37
     lamp
    0.37
    POSITIVE LOGITS
     laborales
    0.50
    后悔
    0.50
     用户
    0.49
     フロント
    0.48
     mei
    0.47
     동일
    0.47
     biologie
    0.47
     hrvats
    0.47
    𝔯
    0.46
    orragie
    0.46
    Activations Density 0.000%

    No Known Activations