© 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. 221763
    Prev
    Next
    INDEX
    Explanations

    showing you, county, seminars, period, not, software, massages, therefore

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

    without consent

    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
     np
    0.54
     Ralf
    0.54
     👋
    0.53
     Synth
    0.52
    🧍
    0.52
     signer
    0.51
     När
    0.51
     Shopify
    0.50
     Warum
    0.50
     Weyl
    0.49
    POSITIVE LOGITS
    ت
    0.51
    pollution
    0.50
    ח
    0.49
    etheless
    0.48
    arrage
    0.47
    rated
    0.46
    textAppearance
    0.46
    t
    0.45
    igura
    0.44
    imb
    0.44
    Activations Density 0.001%

    No Known Activations