© 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. 22-GEMMASCOPE-RES-131K
    7. 35114
    Prev
    Next
    INDEX
    Explanations

    frequency and timing

    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_22/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
     their
    -1.40
    几年
    -1.02
    jScrollPane
    -0.99
    遞
    -0.97
    Filmography
    -0.94
    ánk
    -0.93
    覺
    -0.93
    駅から
    -0.92
    ⅛
    -0.91
    Fest
    -0.91
    POSITIVE LOGITS
     will
    1.50
     hopefully
    1.48
    hopefully
    1.34
    Hopefully
    1.32
     desenhos
    1.30
     anúncios
    1.24
    媗
    1.23
     my
    1.20
    probably
    1.18
     consacré
    1.13
    Activations Density 0.055%

    No Known Activations