© 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. 245592
    Prev
    Next
    INDEX
    Explanations

    holy or sacred words

    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
     insidious
    0.50
    но
    0.49
    ט
    0.48
    ール
    0.46
     pests
    0.46
    *:
    0.46
     delicacy
    0.45
    та
    0.44
    ца
    0.44
    ®.
    0.44
    POSITIVE LOGITS
    主教
    0.51
    伡
    0.49
    reste
    0.47
     እንኳን
    0.46
     পবিত্র
    0.46
    istič
    0.46
     அவனை
    0.46
     ഒരിക്ക
    0.45
    emple
    0.44
     புனித
    0.44
    Activations Density 0.001%

    No Known Activations