© 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. 57836
    Prev
    Next
    INDEX
    Explanations

    angular velocity and resolution

    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
    ajuste
    -0.78
     chevrolet
    -0.74
    وتا
    -0.72
    ecar
    -0.71
    ولايات
    -0.70
    çon
    -0.69
     dreamed
    -0.68
     drž
    -0.68
    shein
    -0.68
     Top
    -0.65
    POSITIVE LOGITS
     velocity
    1.41
     velocidade
    1.28
    velocity
    1.22
     velocities
    1.21
     velocidad
    1.20
     velocidades
    1.04
     Velocity
    1.02
     vel
    1.02
     vitesse
    0.97
    Velocity
    0.96
    Activations Density 0.020%

    No Known Activations