© 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. 22-GEMMASCOPE-RES-131K
    7. 39888
    Prev
    Next
    INDEX
    Explanations

    quantifying scale and magnitude

    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
    Mű
    -1.41
    Elő
    -1.34
     filósofo
    -1.20
     sés
    -1.16
    Čo
    -1.15
     douleurs
    -1.15
    Forrás
    -1.14
     mystère
    -1.09
    identifikasi
    -1.09
    τητα
    -1.09
    POSITIVE LOGITS
     maybe
    1.53
    zegovina
    1.31
     or
    1.30
     if
    1.27
    </em>
    1.20
     sometimes
    1.15
     början
    1.13
     $
    1.11
     percentage
    1.09
     &
    1.08
    Activations Density 0.024%

    No Known Activations