© 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. 143623
    Prev
    Next
    INDEX
    Explanations

    meditating, trust, actually, melts, black, website

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

    claims or certificates

    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
     Edo
    0.54
     obed
    0.51
     El
    0.50
     Allentown
    0.49
     Kd
    0.49
    0.48
     Los
    0.48
     Ö
    0.47
     Conjecture
    0.46
     Deutschen
    0.46
    POSITIVE LOGITS
     খুঁজ
    0.49
     polarised
    0.45
     shimmering
    0.43
     securely
    0.42
    খ্যার
    0.42
     uzyska
    0.42
    ρα
    0.42
     મૂ
    0.42
    த்திரை
    0.42
     swirls
    0.42
    Activations Density 0.000%

    No Known Activations