© 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. 136612
    Prev
    Next
    INDEX
    Explanations

    hatred, victory, support, accepted

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

    preschoolers, complex rule details

    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
    🫡
    0.54
    🫢
    0.46
    anın
    0.45
     lacs
    0.45
    ---
    0.44
    arang
    0.43
    🤌
    0.43
    🛖
    0.42
    ungkinkan
    0.41
    🫶
    0.41
    POSITIVE LOGITS
     hekt
    0.50
     feminists
    0.49
     akadem
    0.49
     infrastrukt
    0.48
     hohen
    0.48
     chubby
    0.46
     स्टार्टिंग
    0.44
    }\!\
    0.44
     feminist
    0.44
     tàu
    0.43
    Activations Density 0.000%

    No Known Activations