© 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. 49572
    Prev
    Next
    INDEX
    Explanations

    religious viewpoint

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

    concept of permanence

    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
     VECTOR
    0.53
     ALSO
    0.45
    σ
    0.44
     vector
    0.44
    ↵↵
    0.44
    ش
    0.43
     ROLL
    0.43
    軍
    0.43
     επίσης
    0.42
    ể
    0.42
    POSITIVE LOGITS
     religiosos
    0.50
     religieux
    0.49
     religi
    0.48
     മത
    0.46
    Religious
    0.46
     परंपरागत
    0.46
     حقیقی
    0.46
    bitos
    0.45
     fréquente
    0.45
     لیتے
    0.44
    Activations Density 0.000%

    No Known Activations