© 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. 22-GEMMASCOPE-RES-131K
    7. 40265
    Prev
    Next
    INDEX
    Explanations

    `fileID`, `TypeInfo`, `CLASS`, `EXTERN`

    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_22/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
     or
    -1.66
     For
    -1.64
     Remember
    -1.61
     Why
    -1.58
    5
    -1.57
     With
    -1.56
     After
    -1.55
     their
    -1.52
    6
    -1.48
     through
    -1.46
    POSITIVE LOGITS
    
    1.65
    がありますが
    1.56
    栳
    1.55
     niemieck
    1.47
    雱
    1.43
    َا
    1.41
    不时
    1.41
    聼
    1.40
     ove
    1.38
    ולוג
    1.37
    Activations Density 0.001%

    No Known Activations