© 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. 78625
    Prev
    Next
    INDEX
    Explanations

    Find, The, Child, homicide

    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
     while
    -0.87
     despite
    -0.78
     <
    -0.70
     dedicar
    -0.69
    ;
    -0.68
    峯
    -0.66
     penderita
    -0.66
    Tweets
    -0.65
    pí
    -0.65
     regardless
    -0.65
    POSITIVE LOGITS
     wx
    1.71
    wx
    1.53
     Wx
    1.03
    Wx
    1.01
     Bhutan
    0.98
    Picker
    0.95
     Ghanaian
    0.94
     getApp
    0.94
    niana
    0.94
    EMY
    0.92
    Activations Density 0.030%

    No Known Activations