© 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. 10163
    Prev
    Next
    INDEX
    Explanations

    'm'

    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
    ↵
    -3.27
    6
    -2.84
    </u>
    -2.83
    １
    -2.77
    Probably
    -2.75
     для
    -2.73
    4
    -2.67
    事も
    -2.59
    5
    -2.59
    Currently
    -2.55
    POSITIVE LOGITS
     was
    3.48
     '
    2.75
     m
    2.73
    詎
    2.64
     But
    2.61
    
    2.53
    翾
    2.44
    同様に
    2.39
     knows
    2.36
    饪
    2.31
    Activations Density 0.010%

    No Known Activations