© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67221
    Prev
    Next
    INDEX
    Explanations

    neutral

    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
    I
    -2.89
     dejando
    -2.78
     Ive
    -2.42
    indelijk
    -2.38
     tad
    -2.36
     одним
    -2.34
     perdiendo
    -2.33
     üb
    -2.28
     poniendo
    -2.28
    Зно
    -2.27
    POSITIVE LOGITS
    ization
    2.61
    izers
    2.45
    ︲
    2.34
    ‼
    2.30
    phile
    2.23
    preneur
    2.22
    谵
    2.16
    isers
    2.14
    犇
    2.14
    ancing
    2.11
    Activations Density 0.018%

    No Known Activations