© 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. 78828
    Prev
    Next
    INDEX
    Explanations

    C string memory functions

    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
    fortune
    -0.73
     menentukan
    -0.73
    Quali
    -0.71
    cF
    -0.71
    ोजना
    -0.70
    jiga
    -0.70
    Dopo
    -0.69
    topatho
    -0.68
    weza
    -0.67
    sellor
    -0.66
    POSITIVE LOGITS
    memset
    4.09
     remember
    2.61
     mem
    2.55
     remembers
    2.52
     remembered
    2.41
     remembrance
    2.28
     memory
    2.28
     remembering
    2.25
     Remember
    2.22
    remember
    2.09
    Activations Density 0.021%

    No Known Activations