© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35125
    Prev
    Next
    INDEX
    Explanations

    type, indication, implant

    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
     belge
    -1.48
    𖧵
    -1.46
     فقط
    -1.27
    Ӏ
    -1.25
     یا
    -1.25
    
    -1.25
    voted
    -1.24
    ributes
    -1.24
    ystemen
    -1.23
    aroo
    -1.23
    POSITIVE LOGITS
     how
    2.88
     whether
    2.22
     time
    1.91
     number
    1.91
     possible
    1.88
     where
    1.85
     length
    1.79
     type
    1.78
     required
    1.73
     size
    1.72
    Activations Density 0.071%

    No Known Activations