© 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. 93071
    Prev
    Next
    INDEX
    Explanations

    statutory be an, which means

    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
     Tinggi
    -0.83
     Pemer
    -0.80
     *"
    -0.78
    âmica
    -0.77
     끝
    -0.77
     схо
    -0.76
    void
    -0.75
    tická
    -0.75
    centric
    -0.74
    原始内容存档于
    -0.73
    POSITIVE LOGITS
     it
    1.38
     its
    1.10
     handelt
    0.99
     vì
    0.98
     noin
    0.97
     something
    0.94
     there
    0.92
     ilgi
    0.91
    ELTS
    0.91
     obti
    0.84
    Activations Density 0.094%

    No Known Activations