© 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. 99903
    Prev
    Next
    INDEX
    Explanations

    jade garden, color, templating engine, hailie mathers, jaded

    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
    ).
    -3.02
    ↵↵
    -3.00
    嗵
    -2.89
    唞
    -2.84
     \%$.
    -2.66
    甡
    -2.58
     That
    -2.56
    ांकि
    -2.47
     admirable
    -2.36
    鸰
    -2.31
    POSITIVE LOGITS
    頃の
    2.50
    薆
    2.47
    Compared
    2.33
    ኧ
    2.33
     
    2.31
     главный
    2.27
    t
    2.27
    On
    2.27
     stalwart
    2.25
    觏
    2.22
    Activations Density 0.002%

    No Known Activations