© 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. 95704
    Prev
    Next
    INDEX
    Explanations

    director, company, round, service, feature

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

    glass, virtual worlds, circles

    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
     تقد
    0.49
     prune
    0.46
     Bewertung
    0.46
     enterprising
    0.46
    cach
    0.45
    𝓮
    0.45
    uk
    0.45
     แปร
    0.45
    ']).
    0.44
     發
    0.44
    POSITIVE LOGITS
    로드
    0.44
    一部分
    0.43
    ρεία
    0.43
    );*/
    0.43
    бол
    0.42
    сть
    0.41
    دا
    0.41
    בל
    0.41
    ద్ర
    0.41
    λία
    0.40
    Activations Density 0.001%

    No Known Activations