© 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. 145951
    Prev
    Next
    INDEX
    Explanations

    strategic thinking, highest good, organically farmed

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

    you, mortal, entity, extended

    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
    ך
    0.47
     начи
    0.46
    лей
    0.45
    пру
    0.44
     obtenir
    0.44
    解消
    0.44
    ตั้ง
    0.43
    รอง
    0.42
     собствен
    0.42
    legi
    0.42
    POSITIVE LOGITS
    am
    0.57
    n
    0.57
     heads
    0.49
    䀖
    0.46
     hea
    0.45
    e
    0.45
     Heads
    0.45
    ాన్
    0.45
    imhe
    0.44
     xD
    0.44
    Activations Density 0.000%

    No Known Activations