© 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. 47418
    Prev
    Next
    INDEX
    Explanations

    rising tensions

    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
     disposto
    -0.93
     coordinated
    -0.89
     damage
    -0.87
     phenomenon
    -0.86
     entusias
    -0.85
     diversified
    -0.84
     übere
    -0.84
     litri
    -0.84
     undertaken
    -0.83
     relentless
    -0.82
    POSITIVE LOGITS
     tension
    1.70
     Tension
    1.52
     tensions
    1.45
    Tension
    1.41
    tension
    1.38
     tensión
    1.30
     tense
    1.26
     tensione
    1.26
    Boiling
    1.26
     Tense
    1.23
    Activations Density 0.019%

    No Known Activations