© 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. 10248
    Prev
    Next
    INDEX
    Explanations

    experimental observations and results

    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
     then
    -2.08
     they
    -1.44
    ></
    -1.38
    ]
    -1.38
    >
    -1.37
     also
    -1.36
     \
    -1.36
    =
    -1.32
     I
    -1.29
    
    -1.27
    POSITIVE LOGITS
     vermi
    1.38
    safari
    1.30
    komt
    1.29
    TryDecode
    1.29
     発売
    1.29
    ühner
    1.28
    勦
    1.27
    ุต
    1.27
     russa
    1.26
    Bref
    1.25
    Activations Density 0.089%

    No Known Activations