© 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. 10-GEMMASCOPE-RES-131K
    7. 15145
    Prev
    Next
    INDEX
    Explanations

    breaking through

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects descriptions of physical penetration or cutting through barriers or obstacles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    </h3>
    -2.11
    </h2>
    -1.74
    ↵↵
    -1.59
    ed
    -1.55
    病人
    -1.49
     bunches
    -1.48
      
    -1.41
    𐐪
    -1.37
    ak
    -1.32
     eloquent
    -1.31
    POSITIVE LOGITS
     the
    1.44
     between
    1.41
    蓠
    1.38
    kiwa
    1.34
    untamiento
    1.33
     showcased
    1.28
     ottenere
    1.27
     двумя
    1.27
     ?>
    1.26
     ujar
    1.26
    Activations Density 0.027%

    No Known Activations