© 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. 78650
    Prev
    Next
    INDEX
    Explanations

    source and destination addresses

    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
     Heinz
    -0.72
     lurking
    -0.71
    স্
    -0.70
    posis
    -0.68
     retort
    -0.68
     ECB
    -0.66
    Fais
    -0.66
    greSQL
    -0.66
     ABD
    -0.65
    eig
    -0.65
    POSITIVE LOGITS
     source
    2.33
     destination
    2.13
     src
    2.02
     Source
    1.91
    src
    1.89
    source
    1.86
     dst
    1.84
    源
    1.84
    Source
    1.78
     Destination
    1.77
    Activations Density 0.057%

    No Known Activations