© 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. 63995
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation

    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
     heavily
    -1.05
     strongly
    -0.98
    logitech
    -0.95
     Beweg
    -0.90
     such
    -0.88
    dropbox
    -0.88
     també
    -0.87
     Unglück
    -0.84
    )}{
    -0.83
    RequestDto
    -0.83
    POSITIVE LOGITS
    tellte
    0.93
     dokonce
    0.92
    ต์
    0.89
    事实上
    0.87
     Pote
    0.87
     cæ
    0.86
     vasi
    0.86
     revan
    0.85
    gged
    0.85
     Babys
    0.85
    Activations Density 0.037%

    No Known Activations