© 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. 113623
    Prev
    Next
    INDEX
    Explanations

    water slides and slide shows

    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
    will
    -1.61
     when
    -1.58
    at
    -1.57
     назва
    -1.46
     increase
    -1.43
     adequately
    -1.41
    after
    -1.38
    when
    -1.34
    Bildung
    -1.34
    although
    -1.32
    POSITIVE LOGITS
    ।
    1.54
    ཊ
    1.53
    ].
    1.48
    螣
    1.47
     into
    1.46
    嫱
    1.45
     sostu
    1.44
     Garantie
    1.42
    INGO
    1.40
     moviliz
    1.40
    Activations Density 0.038%

    No Known Activations