© 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. 79084
    Prev
    Next
    INDEX
    Explanations

    sending message or data

    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
     endured
    -0.92
    ి
    -0.90
     feiner
    -0.87
     farben
    -0.82
    一九
    -0.82
    0
    -0.82
    著
    -0.81
    Extras
    -0.81
     contaba
    -0.81
     extras
    -0.81
    POSITIVE LOGITS
    recv
    1.55
     Send
    1.45
     Sending
    1.21
    Recv
    1.20
     SEND
    1.20
     send
    1.16
    send
    1.14
    tance
    1.13
    ruecos
    1.13
     sending
    1.12
    Activations Density 0.016%

    No Known Activations