© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20619
    Prev
    Next
    INDEX
    Explanations

    about time or finding oneself

    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
    ↵
    -1.63
     innych
    -1.56
    ),
    -1.50
    」「
    -1.49
    In
    -1.45
    The
    -1.45
    ↵↵
    -1.45
     seguintes
    -1.38
    This
    -1.38
     and
    -1.38
    POSITIVE LOGITS
     theſe
    1.57
    んだよね
    1.50
    ۞
    1.47
     poeta
    1.42
    ệnh
    1.41
    趿
    1.40
     adal
    1.40
     datter
    1.38
     it
    1.37
     nader
    1.37
    Activations Density 0.513%

    No Known Activations