© 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. 34-GEMMASCOPE-RES-131K
    7. 115477
    Prev
    Next
    INDEX
    Explanations

    expressing convictions

    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
     nadru
    -1.19
    NNNN
    -1.14
    ujemy
    -1.05
    stwo
    -1.03
    phere
    -1.02
     {*}
    -1.00
     XXXVI
    -0.99
     recent
    -0.98
     tą
    -0.98
    preneur
    -0.97
    POSITIVE LOGITS
     there
    2.02
     no
    1.80
     nothing
    1.80
     every
    1.73
     it
    1.66
     everyone
    1.57
     unless
    1.56
     success
    1.55
     what
    1.47
     anything
    1.47
    Activations Density 0.055%

    No Known Activations