© 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. 9701
    Prev
    Next
    INDEX
    Explanations

    advance internet, totally made

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

    software defined

    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
     बरामद
    0.35
     Rape
    0.32
    甄
    0.32
     Vulcan
    0.31
     Astral
    0.31
     наход
    0.31
    萜
    0.31
    гал
    0.31
     سرا
    0.31
    רץ
    0.31
    POSITIVE LOGITS
     floors
    0.35
    ㄟ
    0.34
    Equals
    0.34
     sinds
    0.33
     serveur
    0.32
     facilitates
    0.32
     যখন
    0.31
     giugno
    0.31
     hanger
    0.31
    চিত্রে
    0.31
    Activations Density 0.000%

    No Known Activations