© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108528
    Prev
    Next
    INDEX
    Explanations

    bending and bent

    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
    ized
    -0.86
     κατα
    -0.85
     underlined
    -0.83
    tains
    -0.81
     sababu
    -0.81
     kutumia
    -0.80
    anyuan
    -0.80
    se
    -0.80
    ショ
    -0.79
     organizza
    -0.79
    POSITIVE LOGITS
     bend
    1.84
     bending
    1.83
     Bending
    1.77
     Bend
    1.74
     bends
    1.67
    bend
    1.67
    Bend
    1.51
     bent
    1.48
    bending
    1.45
    bent
    1.39
    Activations Density 0.008%

    No Known Activations