© 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. 236133
    Prev
    Next
    INDEX
    Explanations

    year, out, protection, until, plans

    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
    Kwa
    0.51
     受け
    0.50
     যোগ্য
    0.48
     GoName
    0.48
     Pasand
    0.47
    𒈗
    0.46
     Kür
    0.46
     ஒழு
    0.45
    dür
    0.44
     പ്രാ
    0.44
    POSITIVE LOGITS
    αιο
    0.48
    <blockquote>
    0.45
    /
    0.43
     Hurricanes
    0.41
    n
    0.41
    苍
    0.39
     ½
    0.39
    ズム
    0.39
    乘以
    0.39
     rearview
    0.39
    Activations Density 0.001%

    No Known Activations