© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5079
    Prev
    Next
    INDEX
    Explanations

    regression, prediction, and causal effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carnot
    0.88
     බෙ
    0.88
     equilateral
    0.85
    锟
    0.85
     kul
    0.82
     perceptual
    0.82
     придума
    0.79
     Boltzmann
    0.78
    堺
    0.78
     Ferenc
    0.76
    POSITIVE LOGITS
     estimada
    0.78
     estimados
    0.72
    г
    0.67
    τές
    0.64
     forecast
    0.64
     Forecast
    0.63
     forecasts
    0.63
    ández
    0.62
     regression
    0.62
     múlt
    0.62
    Activations Density 0.359%

    No Known Activations