© 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. 92958
    Prev
    Next
    INDEX
    Explanations

    direction and spatial component

    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
     crucial
    -0.94
     TextFormField
    -0.87
     bizarre
    -0.86
     Chet
    -0.83
    minu
    -0.82
     بد
    -0.82
     vgl
    -0.81
     cozin
    -0.81
     odw
    -0.80
     rechte
    -0.79
    POSITIVE LOGITS
     dimension
    1.06
     component
    1.04
     direction
    0.99
     and
    0.92
     протя
    0.84
    Dimension
    0.83
     pohled
    0.82
    方向
    0.81
    dimension
    0.81
    ity
    0.80
    Activations Density 0.073%

    No Known Activations