© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66752
    Prev
    Next
    INDEX
    Explanations

    location / to be found

    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
    </strong>
    -2.08
     sombr
    -2.03
    "
    -1.98
    
    -1.91
     valla
    -1.88
    鰱
    -1.86
     Antwerpen
    -1.85
    a
    -1.84
    が
    -1.84
    значно
    -1.82
    POSITIVE LOGITS
     and
    2.91
     or
    2.05
     burbujas
    1.85
    siamo
    1.84
     unglaub
    1.82
    
    1.80
    様な
    1.75
     huellas
    1.75
    alberto
    1.73
     見える
    1.71
    Activations Density 0.004%

    No Known Activations