© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76960
    Prev
    Next
    INDEX
    Explanations

    reserved ports

    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
    ляются
    -0.98
    turquoise
    -0.97
     Akte
    -0.96
    dpy
    -0.91
     höl
    -0.91
    lafen
    -0.91
    Obviously
    -0.89
    ristmas
    -0.89
    uesday
    -0.88
    tagna
    -0.88
    POSITIVE LOGITS
     خریدار
    1.38
    bus
    1.23
    _
    1.15
     bus
    1.13
    port
    1.08
     riktigt
    1.06
    Reserved
    1.03
     reserved
    1.02
     port
    1.02
     ports
    1.01
    Activations Density 0.009%

    No Known Activations