© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9476
    Prev
    Next
    INDEX
    Explanations

    numbers and ranges with units

    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_10/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
     "").
    -1.35
     neither
    -1.34
    )':
    -1.28
     only
    -1.22
     schild
    -1.20
    -
    
    -1.20
    '&
    -1.19
     mê
    -1.19
    only
    -1.17
    "=>
    -1.13
    POSITIVE LOGITS
     Each
    1.24
     через
    1.23
     a
    1.23
    forcement
    1.22
    Get
    1.21
    Each
    1.20
     of
    1.16
     each
    1.10
    Here
    1.09
     neue
    1.09
    Activations Density 0.110%

    No Known Activations