© 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. 31314
    Prev
    Next
    INDEX
    Explanations

    pointer and ptr

    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
    YY
    -0.78
     Ingles
    -0.74
     Resili
    -0.73
     축
    -0.73
     PES
    -0.72
    笥
    -0.71
     Pensacola
    -0.71
     objectivity
    -0.70
    norr
    -0.70
    copus
    -0.70
    POSITIVE LOGITS
     uintptr
    1.01
     pointer
    0.95
    ptr
    0.93
     ptr
    0.93
    PTR
    0.90
    Ptr
    0.83
    uintptr
    0.82
    pointer
    0.80
     pet
    0.78
    指针
    0.77
    Activations Density 0.174%

    No Known Activations