© 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. 32549
    Prev
    Next
    INDEX
    Explanations

    accounts of past events

    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
     continuer
    -1.58
     continually
    -1.50
    continue
    -1.46
     still
    -1.37
     eventually
    -1.36
     weiterhin
    -1.35
     stále
    -1.33
    继续
    -1.32
     continuamente
    -1.30
     continuant
    -1.29
    POSITIVE LOGITS
     attempted
    1.37
     hubo
    1.27
     visit
    1.26
     see
    1.22
     EVER
    1.21
     richtig
    1.20
     mention
    1.20
     tried
    1.17
     hear
    1.17
     ever
    1.17
    Activations Density 0.033%

    No Known Activations