© 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. 103387
    Prev
    Next
    INDEX
    Explanations

    methods and processes

    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
     for
    -2.17
     like
    -1.93
     would
    -1.78
     didn
    -1.58
     still
    -1.51
     should
    -1.49
     liked
    -1.38
     who
    -1.37
     with
    -1.36
     initially
    -1.34
    POSITIVE LOGITS
     بعض
    1.57
    decisions
    1.41
    ſſi
    1.39
     religiosas
    1.36
    conditions
    1.36
     มิ
    1.35
    depends
    1.34
    踅
    1.32
    Procedimento
    1.31
    fair
    1.30
    Activations Density 0.236%

    No Known Activations