© 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. 10-GEMMASCOPE-RES-131K
    7. 42927
    Prev
    Next
    INDEX
    Explanations

    losses in or of

    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
    
    -3.23
    ’
    -2.56
    甞
    -2.53
    蟊
    -2.52
    irmanship
    -2.38
    tividade
    -2.28
    "=>$
    -2.27
    '),
    -2.23
    ндарт
    -2.22
    commodation
    -2.20
    POSITIVE LOGITS
    3
    2.95
    6
    2.89
    8
    2.88
    5
    2.78
    4
    2.58
    2
    2.55
    りする
    2.55
    7
    2.53
    時も
    2.53
     losses
    2.52
    Activations Density 0.005%

    No Known Activations