© 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. 242802
    Prev
    Next
    INDEX
    Explanations

    God and spiritual concepts

    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
    モチ
    0.49
    運動
    0.49
     rein
    0.45
    キス
    0.45
    த
    0.45
     эксперимента
    0.45
    メ
    0.44
    ー
    0.44
    リング
    0.43
    pivot
    0.43
    POSITIVE LOGITS
    orske
    0.48
     änd
    0.44
    的服务
    0.44
     erkl
    0.43
    গোষ্ঠ
    0.42
     وغير
    0.42
    权利
    0.42
     poprzed
    0.42
     وحده
    0.41
     Clauses
    0.41
    Activations Density 0.001%

    No Known Activations