© 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. 42096
    Prev
    Next
    INDEX
    Explanations

    numbered list items

    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
    𝄆
    -1.64
     posteriormente
    -1.63
    佮
    -1.59
     verdaderamente
    -1.59
     wykonane
    -1.58
     obviamente
    -1.56
     opcional
    -1.54
     particularmente
    -1.52
    Љ
    -1.48
     específicamente
    -1.46
    POSITIVE LOGITS
    :
    1.99
    }
    1.77
    ING
    1.64
    AL
    1.61
    _{
    1.58
    2
    1.56
    AN
    1.52
    1.52
    ’,
    1.52
    ON
    1.52
    Activations Density 0.012%

    No Known Activations