© 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. 14028
    Prev
    Next
    INDEX
    Explanations

    stream in code or media

    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
    𖣘
    -3.20
    0
    -3.00
    7
    -2.95
    8
    -2.92
    and
    -2.88
    4
    -2.83
    苤
    -2.81
     penso
    -2.78
    在他的
    -2.75
    5
    -2.70
    POSITIVE LOGITS
    इटम
    2.81
    viembre
    2.69
    氩
    2.67
    鉝
    2.64
    当下
    2.63
    ),
    2.59
    趼
    2.53
     gelb
    2.50
    传统的
    2.48
    فرة
    2.48
    Activations Density 0.011%

    No Known Activations