© 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. 125384
    Prev
    Next
    INDEX
    Explanations

    required, all, expressed, enjoying

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

    ordering subscription boxes

    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
    И
    0.51
    鯽
    0.47
    因素
    0.46
    ifndef
    0.46
    })^{\
    0.46
     }^{\
    0.45
    আই
    0.44
    簡単に
    0.44
    ఐ
    0.44
    ఎ
    0.43
    POSITIVE LOGITS
     doorstep
    0.47
     diambil
    0.46
    Locations
    0.46
     misty
    0.43
     चित्रों
    0.42
    óricos
    0.42
    Trim
    0.42
     strewn
    0.42
     swath
    0.42
     ‘’
    0.42
    Activations Density 0.001%

    No Known Activations