© 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. 34-GEMMASCOPE-RES-131K
    7. 57301
    Prev
    Next
    INDEX
    Explanations

    proposed rule or notice

    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_34/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
    סים
    -0.70
    awak
    -0.69
    Agre
    -0.68
    akers
    -0.68
     space
    -0.66
     strap
    -0.65
    Completion
    -0.65
     iLocal
    -0.64
     normalized
    -0.64
    ABULARY
    -0.64
    POSITIVE LOGITS
     rule
    1.66
     comment
    1.66
     proposed
    1.64
     notice
    1.50
     Comment
    1.48
     Proposed
    1.46
     proposing
    1.45
     comments
    1.45
    comment
    1.44
    Comment
    1.43
    Activations Density 0.043%

    No Known Activations