© 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. 174598
    Prev
    Next
    INDEX
    Explanations

    religious/divine authority and obedience

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

    comprehending, mentoring, and collective evaluation

    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
    麥
    0.55
    وز
    0.51
    標準
    0.48
     نط
    0.47
    ين
    0.46
    ث
    0.45
    進入
    0.45
    OEM
    0.45
    冚
    0.44
    ما
    0.44
    POSITIVE LOGITS
    eli
    0.46
     좋
    0.42
    เลย
    0.41
    communication
    0.41
     ล่ะ
    0.41
    ırl
    0.40
     нас
    0.40
    breviation
    0.40
     فنا
    0.40
    ésar
    0.39
    Activations Density 0.001%

    No Known Activations