© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42359
    Prev
    Next
    INDEX
    Explanations

    negative evaluations and criticisms

    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_10/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
     betyd
    -1.41
     Händen
    -1.38
     abbiamo
    -1.35
    Bjs
    -1.34
    ironically
    -1.31
     anledning
    -1.30
    oeuvre
    -1.30
    čené
    -1.29
    下載
    -1.28
    hmmmm
    -1.28
    POSITIVE LOGITS
     and
    2.16
     "
    1.78
     to
    1.74
     then
    1.50
     if
    1.48
     и
    1.42
     would
    1.36
     all
    1.34
     &
    1.31
    }
    1.30
    Activations Density 0.098%

    No Known Activations