© 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. 116926
    Prev
    Next
    INDEX
    Explanations

    damage and its consequences

    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
     détaillés
    -1.16
    цію
    -1.09
     horloge
    -1.07
    Με
    -1.01
    Мария
    -1.00
    퐼
    -0.99
    驒
    -0.99
    ⓒ
    -0.99
     loam
    -0.98
     externes
    -0.97
    POSITIVE LOGITS
     done
    1.89
     inflicted
    1.36
     repair
    1.30
     irreparable
    1.28
     repaired
    1.27
     incurred
    1.25
     Repair
    1.22
     Done
    1.16
     caused
    1.16
    Done
    1.12
    Activations Density 0.027%

    No Known Activations