© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30450
    Prev
    Next
    INDEX
    Explanations

    loss function jargon

    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_34/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
     dijeron
    -0.90
     vieron
    -0.90
     convierte
    -0.82
     ECTS
    -0.78
     ciò
    -0.77
    鳢
    -0.77
     vicina
    -0.76
     mueve
    -0.74
     Inoltre
    -0.73
     ICM
    -0.73
    POSITIVE LOGITS
     loss
    2.59
     losses
    2.39
     Loss
    2.09
     Losses
    2.02
    Loss
    2.02
    loss
    1.85
     LOSS
    1.74
    LOSS
    1.73
    losses
    1.72
    Losses
    1.58
    Activations Density 0.003%

    No Known Activations