© 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. 78168
    Prev
    Next
    INDEX
    Explanations

    pleaded guilty

    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
     whilst
    -2.19
     Whilst
    -2.13
    Whilst
    -2.08
     Amongst
    -1.69
    twelve
    -1.56
     amongst
    -1.53
     twenty
    -1.52
     twentieth
    -1.51
     sixty
    -1.51
     twelve
    -1.51
    POSITIVE LOGITS
     —
    1.55
    cq
    1.35
     --
    1.34
     amid
    1.32
     ZIP
    1.30
     Wednesday
    1.29
     нынеш
    1.28
     

    1.27
     Sept
    1.24
     
    1.23
    Activations Density 1.024%

    No Known Activations