© 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. 63316
    Prev
    Next
    INDEX
    Explanations

    relay protection

    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
     aislamiento
    -0.75
     DAILY
    -0.73
     Sinai
    -0.73
    اهش
    -0.73
    cusa
    -0.72
    bés
    -0.72
    ὑ
    -0.71
    喊道
    -0.71
     tør
    -0.71
    DAILY
    -0.71
    POSITIVE LOGITS
     relay
    1.36
     protection
    1.21
    relay
    1.20
     Relay
    1.13
     relays
    1.09
    Relay
    1.08
     protect
    0.99
     protections
    0.97
     prote
    0.92
    protection
    0.90
    Activations Density 0.017%

    No Known Activations