© 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. 14206
    Prev
    Next
    INDEX
    Explanations

    Centromeres, css, M_Object_, out

    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
    ַּ
    -1.12
    ִּ
    -1.02
    Tras
    -0.99
    越來越
    -0.93
     قوات
    -0.92
    简称
    -0.92
    ÈNE
    -0.91
    变
    -0.91
     моя
    -0.90
    fitri
    -0.90
    POSITIVE LOGITS
     there
    1.78
     出演
    1.16
     terdapat
    1.15
     portátiles
    1.15
    らかに
    1.13
    铣
    1.12
     ciertos
    1.09
     behauptet
    1.08
     theſe
    1.05
     ciertas
    1.05
    Activations Density 0.021%

    No Known Activations