© 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. 111495
    Prev
    Next
    INDEX
    Explanations

    rights, moments, code, integration

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

    Religious Perspectives

    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
    ulle
    0.50
    runners
    0.47
    ം
    0.46
    ida
    0.45
    oti
    0.45
    튼
    0.45
    otos
    0.45
    rafish
    0.44
    icol
    0.44
    cards
    0.44
    POSITIVE LOGITS
     සම්බන්ධ
    0.50
    倆
    0.47
     πολι
    0.45
     bağlan
    0.45
    妘
    0.45
     नियंत्रित
    0.44
     Verfahren
    0.44
    制御
    0.44
     කි
    0.43
     mislead
    0.43
    Activations Density 0.000%

    No Known Activations