© 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. 139507
    Prev
    Next
    INDEX
    Explanations

    describe quality or welcome

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

    introducing or explaining 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
     aufgenommen
    0.50
    она
    0.47
     đột
    0.47
    ارڈ
    0.47
    }]_{
    0.46
     ক্লাস
    0.46
    }^{-
    0.46
    मनी
    0.45
    FileInput
    0.45
    }']
    0.45
    POSITIVE LOGITS
    fl
    0.50
    什么是
    0.46
    رحب
    0.46
    商品説明
    0.46
    欢迎
    0.45
     Quality
    0.45
     Awards
    0.45
     Gourmet
    0.45
    壓
    0.44
    quality
    0.44
    Activations Density 0.001%

    No Known Activations