© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2764
    Prev
    Next
    INDEX
    Explanations

    statistical regression models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     localStorage
    0.83
    ♿
    0.75
     Consciousness
    0.71
     باور
    0.70
    Elon
    0.65
    localStorage
    0.65
     MCU
    0.65
    firestore
    0.64
    兌
    0.64
     entsch
    0.64
    POSITIVE LOGITS
     regression
    1.62
     Regression
    1.56
    Regression
    1.43
     regressions
    1.40
    regression
    1.31
     ggplot
    1.26
     regres
    1.26
     estimation
    1.22
    Estimation
    1.22
     Estimation
    1.22
    Activations Density 0.538%

    No Known Activations