© 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. 166043
    Prev
    Next
    INDEX
    Explanations

    saying Jesus

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

    question/answer prompts

    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
    antaranya
    0.54
    ни
    0.50
     CONGRESS
    0.49
    apadam
    0.46
    iteness
    0.46
    лося
    0.45
     гале
    0.45
    h
    0.45
    騁
    0.45
    리카
    0.45
    POSITIVE LOGITS
     Age
    0.53
    Age
    0.52
    ،
    0.47
    Week
    0.47
    ，
    0.47
    Safety
    0.44
     hopeful
    0.43
     age
    0.43
    Enemy
    0.43
     Potential
    0.42
    Activations Density 0.001%

    No Known Activations