© 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. 78425
    Prev
    Next
    INDEX
    Explanations

    Face of words

    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
    乘
    -0.85
    ゞ
    -0.81
     × 
    -0.81
     fragility
    -0.78
     perchance
    -0.77
    ᛚ
    -0.75
    мед
    -0.75
     záz
    -0.74
     toalha
    -0.74
     працю
    -0.74
    POSITIVE LOGITS
     Fac
    0.81
     {
    0.80
     compens
    0.79
    face
    0.79
    fac
    0.78
    Face
    0.73
     QU
    0.72
    倶
    0.72
     Face
    0.72
    thora
    0.69
    Activations Density 0.025%

    No Known Activations