© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40182
    Prev
    Next
    INDEX
    Explanations

    Court identifiers and numbers

    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
     konus
    -1.12
     регионе
    -1.09
    strukt
    -1.07
     first
    -1.06
    ^(@
    -1.04
     menceritakan
    -1.03
     yöntem
    -1.02
    prakti
    -1.02
     varios
    -1.00
    gráficos
    -0.99
    POSITIVE LOGITS
    殃
    1.22
     pretrained
    1.14
    parer
    1.09
    Джере
    1.08
     Ansatz
    1.07
    ciais
    1.07
    饜
    1.05
    ;';
    1.05
     ライフ
    1.05
    '.$
    1.05
    Activations Density 0.011%

    No Known Activations