© 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. 22-GEMMASCOPE-RES-131K
    7. 34647
    Prev
    Next
    INDEX
    Explanations

    strict rules and obligations

    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
     we
    -1.09
    するの
    -1.06
     already
    -1.06
    umenten
    -1.04
     our
    -1.02
    hrter
    -1.02
     variasi
    -0.96
    empio
    -0.96
     naše
    -0.94
     alimony
    -0.94
    POSITIVE LOGITS
     rigidly
    1.39
     strict
    1.25
     strictly
    1.23
    不允许
    1.19
     forbidden
    1.16
    Rigid
    1.09
     their
    1.07
     строго
    1.05
    rigid
    1.05
    controlled
    1.03
    Activations Density 0.048%

    No Known Activations