© 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. 34-GEMMASCOPE-RES-131K
    7. 32344
    Prev
    Next
    INDEX
    Explanations

    not necessarily a problem

    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_34/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
    -1.60
     also
    -1.24
     sowohl
    -1.07
    ený
    -1.03
    そして
    -1.03
     both
    -1.01
    UMNS
    -0.95
     גם
    -0.94
     sogenannte
    -0.94
    无论
    -0.93
    POSITIVE LOGITS
     per
    2.83
     necessarily
    2.63
     exactly
    2.14
    necessarily
    2.03
    exactly
    1.95
    Exactly
    1.80
     nor
    1.72
     necesariamente
    1.68
     perse
    1.64
     Exactly
    1.45
    Activations Density 0.068%

    No Known Activations