© 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. 116478
    Prev
    Next
    INDEX
    Explanations

    playbook offenses and schemes

    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
     dettaglio
    -0.79
    Ấ
    -0.78
     abbigliamento
    -0.75
     essi
    -0.75
     borsa
    -0.74
     livello
    -0.73
    ités
    -0.73
     fiori
    -0.72
     acque
    -0.71
     azzurro
    -0.71
    POSITIVE LOGITS
     system
    1.51
     offense
    1.50
     scheme
    1.36
     sistema
    1.25
     schemes
    1.23
     esquema
    1.23
     offenses
    1.20
     offence
    1.16
    scheme
    1.16
     Scheme
    1.15
    Activations Density 0.021%

    No Known Activations