© 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. 31436
    Prev
    Next
    INDEX
    Explanations

    superficial and shallow depths

    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
     ก็
    -1.01
    стал
    -0.87
     sorriso
    -0.79
    —¿
    -0.79
    ORK
    -0.76
     ไม่มี
    -0.75
     interessantes
    -0.75
    leyin
    -0.75
     จะ
    -0.75
    FEA
    -0.75
    POSITIVE LOGITS
     shallow
    1.48
    shallow
    1.41
    Shallow
    1.29
     Shallow
    1.20
     (<
    1.02
     penetration
    1.01
     shallo
    0.96
     flach
    0.96
    rooted
    0.96
    boxylic
    0.96
    Activations Density 0.021%

    No Known Activations