© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3939
    Prev
    Next
    INDEX
    Explanations

    floors and levels

    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_65k_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
     अभ्यर्थी
    0.69
     बॉर्डर
    0.66
    ખ્યા
    0.65
    ウト
    0.62
     Padilla
    0.61
    nSamples
    0.60
     ද
    0.60
    рисов
    0.60
     Border
    0.59
     border
    0.58
    POSITIVE LOGITS
     floors
    3.52
     floor
    3.41
    floor
    3.09
     Floor
    3.05
    Floor
    3.03
     Floors
    2.89
     FLOOR
    2.65
     flooring
    2.51
     étage
    2.49
    층
    2.41
    Activations Density 0.138%

    No Known Activations