© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21410
    Prev
    Next
    INDEX
    Explanations

    previous status or role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -3.19
    鱨
    -2.63
     '
    -2.59
    はこの
    -2.56
     I
    -2.48
    放心
    -2.45
    튿
    -2.39
    *
    -2.36
     אשר
    -2.31
     други
    -2.27
    POSITIVE LOGITS
    The
    3.36
     Former
    3.06
     Previously
    3.00
     Additionally
    2.98
    However
    2.95
    媄
    2.77
     namun
    2.75
    睒
    2.72
    我一直
    2.72
     Obviously
    2.72
    Activations Density 0.018%

    No Known Activations