© 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. 10-GEMMASCOPE-RES-131K
    7. 75730
    Prev
    Next
    INDEX
    Explanations

    true/false assignments

    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
     their
    -1.39
     from
    -1.31
    -1.27
     that
    -1.23
    瀟
    -1.22
     these
    -1.20
    おそらく
    -1.19
     jopa
    -1.18
     может
    -1.15
    聾
    -1.14
    POSITIVE LOGITS
     somewhat
    1.66
     japonés
    1.52
    ähig
    1.41
     possibility
    1.39
     anderem
    1.38
     options
    1.38
     différents
    1.36
    tická
    1.35
     mode
    1.34
     возможность
    1.34
    Activations Density 0.032%

    No Known Activations