© 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. 57815
    Prev
    Next
    INDEX
    Explanations

    creative alliances

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

    Gods, afterlife, fantasy worlds

    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
     đặt
    0.40
     অধ্যক্ষ
    0.40
     projecting
    0.39
     Cummings
    0.39
     impressing
    0.39
     cargoes
    0.38
     將
    0.38
     sharps
    0.38
    ట్టు
    0.38
     callers
    0.38
    POSITIVE LOGITS
    자
    0.54
    hers
    0.48
    happiness
    0.47
    re
    0.46
    चर्स
    0.46
    ج
    0.46
    bali
    0.45
    이야
    0.45
    Can
    0.45
    cure
    0.44
    Activations Density 0.000%

    No Known Activations