© 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-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 3158
    Prev
    Next
    INDEX
    Explanations

    only purely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    پ
    1.06
     ALLOYS
    0.89
    ０
    0.88
     akibat
    0.87
    ;
    0.86
    嵐
    0.86
     aggi
    0.86
     inclinations
    0.86
     utilisateur
    0.85
     anions
    0.85
    POSITIVE LOGITS
     лишь
    0.93
    с
    0.86
    </h2>
    0.82
    </h3>
    0.82
    ä
    0.80
    </h6>
    0.79
    ním
    0.78
    的技术
    0.77
    س
    0.77
    ES
    0.75
    Activations Density 0.239%

    No Known Activations