© 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. 48506
    Prev
    Next
    INDEX
    Explanations

    coordinates and degree symbols

    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
     by
    -0.96
     longstanding
    -0.92
    ندر
    -0.87
     Truppen
    -0.82
     became
    -0.82
     ostensibly
    -0.82
    Perhaps
    -0.81
    取締
    -0.81
     鐵
    -0.81
     swiftly
    -0.80
    POSITIVE LOGITS
    picion
    0.96
     pozosta
    0.94
    についても
    0.91
     demás
    0.90
    encore
    0.87
     gleichen
    0.86
    Numéro
    0.85
     intric
    0.84
    ourced
    0.81
    ኝ
    0.81
    Activations Density 0.004%

    No Known Activations