© 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. 41066
    Prev
    Next
    INDEX
    Explanations

    web application UI controls

    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
     it
    -1.77
     until
    -1.76
     or
    -1.68
     then
    -1.65
     its
    -1.58
     while
    -1.55
     when
    -1.49
     alongside
    -1.43
     some
    -1.41
     compagni
    -1.41
    POSITIVE LOGITS
     unangemess
    1.78
    You
    1.64
    If
    1.48
    鹮
    1.46
    に
    1.43
    IVENESS
    1.41
     pido
    1.40
    only
    1.38
    ほとんど
    1.38
    醞
    1.38
    Activations Density 0.035%

    No Known Activations