© 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. 234428
    Prev
    Next
    INDEX
    Explanations

    furniture, decor, home design

    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
     Boga
    0.50
    ǒ
    0.47
     on
    0.46
    ீரி
    0.44
    户外
    0.43
     pater
    0.43
    ahun
    0.42
     activa
    0.41
     gusta
    0.41
    تيب
    0.41
    POSITIVE LOGITS
    जीत
    0.49
     県
    0.48
     görüntü
    0.46
    
    0.44
     एमएस
    0.44
    MOND
    0.43
    目的地
    0.43
     कैलो
    0.43
     کاروبار
    0.42
     なお
    0.42
    Activations Density 0.001%

    No Known Activations