© 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. 71734
    Prev
    Next
    INDEX
    Explanations

    for positive contributions

    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
    ：……
    -1.15
    licopter
    -1.10
     only
    -1.09
     проє
    -1.05
    collant
    -1.05
    anganronpa
    -1.03
    :
    -1.01
     entraîne
    -1.00
     other
    -0.99
     that
    -0.99
    POSITIVE LOGITS
     help
    1.40
     support
    1.30
    gebras
    1.27
     assistance
    1.24
     hjelpe
    1.21
     hjælpe
    1.20
    engeti
    1.16
     technical
    1.14
    ช่วย
    1.13
     membantu
    1.12
    Activations Density 0.018%

    No Known Activations