© 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. 52077
    Prev
    Next
    INDEX
    Explanations

    secret chambers

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

    respect and care for self

    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
    inios
    0.49
     Álvarez
    0.46
    фесси
    0.45
     ТО
    0.44
     Украине
    0.44
    скохозяй
    0.44
    譬
    0.44
    栃
    0.43
    僉
    0.42
    ennials
    0.42
    POSITIVE LOGITS
     or
    0.56
     ตัว
    0.54
     shen
    0.54
     bav
    0.54
     tę
    0.52
     기타
    0.51
     tighten
    0.51
     dà
    0.51
     இழ
    0.50
     文字
    0.50
    Activations Density 0.000%

    No Known Activations