© 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. 164482
    Prev
    Next
    INDEX
    Explanations

    few months; Specter; custom properties; gay; sexual

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

    spunk, tinder, spar, injury

    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
    {}'.
    0.47
    vus
    0.43
    聞き
    0.42
    다가
    0.41
    de
    0.40
    পোর্ট
    0.40
    ди
    0.40
     leaped
    0.40
    నకు
    0.40
    🧇
    0.40
    POSITIVE LOGITS
    irthday
    0.49
    ‌ها
    0.47
    ählen
    0.46
    ौ
    0.45
    ة
    0.44
    elé
    0.43
    wifery
    0.43
     ejercer
    0.42
    ախ
    0.42
    قتها
    0.42
    Activations Density 0.000%

    No Known Activations