© 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. 130031
    Prev
    Next
    INDEX
    Explanations

    connecting colors

    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
    erobic
    -1.42
    があるので
    -1.14
     SECOND
    -1.13
     luxus
    -1.11
     univerz
    -1.11
     النوع
    -1.11
    exists
    -1.10
    鶿
    -1.10
    else
    -1.10
     procedure
    -1.09
    POSITIVE LOGITS
     imidlertid
    1.05
    涝
    1.00
     reman
    0.98
     اللون
    0.98
    DUN
    0.97
     only
    0.96
    ׇ
    0.95
     valgt
    0.94
     mandible
    0.92
     religieuses
    0.92
    Activations Density 0.028%

    No Known Activations