© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130336
    Prev
    Next
    INDEX
    Explanations

    introducing additional points

    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
     and
    -1.99
     in
    -1.77
     including
    -1.73
     mostly
    -1.73
    }}=\
    -1.70
    ]))
    
    -1.69
    )):
    
    -1.68
     which
    -1.64
    ’:
    -1.64
    偌
    -1.61
    POSITIVE LOGITS
    ,
    3.06
     econômica
    1.83
    ра
    1.77
     '
    1.54
     The
    1.49
     aéro
    1.48
     \&
    1.44
     financeira
    1.41
     lhes
    1.41
     problemet
    1.41
    Activations Density 0.011%

    No Known Activations