© 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. 77713
    Prev
    Next
    INDEX
    Explanations

    comparative directional terms

    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
     microfibra
    -0.88
     вместо
    -0.85
     против
    -0.85
    来ました
    -0.81
    kundige
    -0.80
     demasi
    -0.77
    raca
    -0.76
     никогда
    -0.76
     извест
    -0.75
    Subsystem
    -0.74
    POSITIVE LOGITS
     farther
    4.53
     further
    4.38
     higher
    3.53
    Further
    3.33
    further
    3.31
     Further
    3.00
     deeper
    2.88
     FURTHER
    2.88
     closer
    2.81
     nearer
    2.80
    Activations Density 0.108%

    No Known Activations