© 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. 110209
    Prev
    Next
    INDEX
    Explanations

    prayer or religious phrases

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

    listing for scenarios

    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
    ană
    0.57
     दुसऱ्या
    0.53
    toNumber
    0.51
    tpVar
    0.50
    uert
    0.50
    馇
    0.49
    लास
    0.49
    anément
    0.49
    umumkan
    0.49
    澤
    0.48
    POSITIVE LOGITS
     I
    0.50
     B
    0.47
     expériment
    0.45
    瑜
    0.45
     hace
    0.45
     martes
    0.44
     griega
    0.44
     wacht
    0.44
     emotion
    0.43
     downt
    0.43
    Activations Density 0.000%

    No Known Activations