© 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. 22-GEMMASCOPE-RES-131K
    7. 15027
    Prev
    Next
    INDEX
    Explanations

    fines, penalties, interest per hour

    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_22/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
     nivelul
    -1.08
     perigo
    -1.03
     frumo
    -1.01
    bullets
    -1.01
    Testo
    -0.97
     unele
    -0.95
     înal
    -0.95
     frumos
    -0.94
    اذ
    -0.94
     brilho
    -0.94
    POSITIVE LOGITS
     penalty
    1.26
    lierung
    1.16
     if
    1.09
     missed
    1.08
    áme
    1.05
     each
    1.05
     lost
    1.05
    开始
    1.01
    animity
    0.97
    odotus
    0.94
    Activations Density 0.010%

    No Known Activations