© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100062
    Prev
    Next
    INDEX
    Explanations

    email me or us

    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
    䊐
    -1.55
    这
    -1.47
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -1.45
    这种
    -1.43
    Además
    -1.39
     هذه
    -1.37
    本来
    -1.36
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.35
    ↵↵↵↵
    -1.34
    This
    -1.34
    POSITIVE LOGITS
     about
    2.75
    蟊
    2.25
     to
    1.52
    ᵴ
    1.51
     dziecka
    1.42
    redning
    1.40
     ...
    1.38
     ότι
    1.38
    涑
    1.38
    redients
    1.37
    Activations Density 0.028%

    No Known Activations