© 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. 68253
    Prev
    Next
    INDEX
    Explanations

    plain string, water, clothes, polymer

    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
     แต่
    -2.63
     десять
    -2.42
    硖
    -2.39
     และ
    -2.33
    咣
    -2.28
     российских
    -2.23
     extraño
    -2.23
    Teléfono
    -2.22
    鲠
    -2.22
    }
    -2.19
    POSITIVE LOGITS
    You
    3.25
    '
    3.06
    1
    2.89
    ."
    2.73
    ֟
    2.72
    x
    2.48
    ൎ
    2.47
    It
    2.44
    m
    2.42
    this
    2.36
    Activations Density 0.019%

    No Known Activations