© 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. 125126
    Prev
    Next
    INDEX
    Explanations

    following Chinese astrology rituals

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

    playlist curators

    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
     ''.
    0.45
    ଛ
    0.45
     respectiv
    0.43
     Ці
    0.43
     பொருட்கள்
    0.43
     controlling
    0.42
     मू
    0.42
    錫
    0.41
    ブレー
    0.41
    ながら
    0.41
    POSITIVE LOGITS
    一张
    0.55
     yeni
    0.47
    }:
    0.47
    忥
    0.47
    т
    0.46
    ടുന്ന
    0.45
    和我
    0.45
    क्वल
    0.44
    全新
    0.44
    的所有
    0.44
    Activations Density 0.001%

    No Known Activations