© 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. 83803
    Prev
    Next
    INDEX
    Explanations

    criminal action

    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
     چیست
    -1.20
     sonda
    -1.14
     pegatinas
    -1.09
     является
    -1.06
     criptomonedas
    -1.03
     ">=
    -1.00
     diskusi
    -0.99
     unglaub
    -0.99
     قوان
    -0.98
     Darn
    -0.98
    POSITIVE LOGITS
     get
    1.26
     got
    1.23
     shit
    1.12
     put
    1.11
     on
    1.05
     thirty
    1.04
     legit
    1.03
     gotta
    1.02
     twenty
    1.01
     fucking
    0.99
    Activations Density 0.057%

    No Known Activations