© 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. 183804
    Prev
    Next
    INDEX
    Explanations

    that always followed by actually

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

    typing, paranoid, APs, lamp, currencies

    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
    ري
    0.43
     Kumar
    0.42
     Poland
    0.42
    UI
    0.42
    Exchange
    0.42
     Francis
    0.40
    律
    0.40
    ifo
    0.39
    的神
    0.39
    ౌ
    0.39
    POSITIVE LOGITS
    penas
    0.52
     प्रतियोग
    0.49
    qualiter
    0.48
     ഇക്കാര
    0.48
    esas
    0.48
    kval
    0.48
    anek
    0.48
     बदले
    0.47
     svog
    0.46
     underdog
    0.46
    Activations Density 0.001%

    No Known Activations