© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30307
    Prev
    Next
    INDEX
    Explanations

    smart contract functions

    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
     цвят
    -0.93
     sputtering
    -0.85
     reinstalling
    -0.81
     dismantled
    -0.78
    infeld
    -0.78
    ällor
    -0.77
    zma
    -0.77
    reus
    -0.76
    ग
    -0.75
     stuttering
    -0.75
    POSITIVE LOGITS
     emergency
    1.03
    checkBox
    0.99
     withdraw
    0.99
     EMERGENCY
    0.90
     transfer
    0.89
     batch
    0.88
     safe
    0.87
    emergency
    0.87
     increase
    0.86
     claim
    0.85
    Activations Density 0.001%

    No Known Activations