© 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. 78209
    Prev
    Next
    INDEX
    Explanations

    movie titles and descriptions

    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
     bia
    -0.78
    newArrayList
    -0.75
    🕦
    -0.75
    lijah
    -0.74
    젝
    -0.72
    frain
    -0.72
     MCL
    -0.71
     Ica
    -0.71
     commentaries
    -0.70
     shunt
    -0.70
    POSITIVE LOGITS
     Coen
    1.16
    txn
    0.85
     Oste
    0.81
    boleh
    0.79
     Nebraska
    0.78
    Missouri
    0.73
     智
    0.73
     işi
    0.73
    营销
    0.73
     hermano
    0.71
    Activations Density 0.016%

    No Known Activations