© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 401
    Prev
    Next
    INDEX
    Explanations

    possessive names or general descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     다음과
    0.65
     выполня
    0.65
    čních
    0.64
     folgende
    0.62
    ña
    0.60
    なります
    0.59
     stycznia
    0.59
    랴
    0.59
     hingegen
    0.59
    臺灣
    0.59
    POSITIVE LOGITS
     head
    0.76
     companion
    0.73
     grandfather
    0.66
     majesty
    0.63
     uncle
    0.63
     cheek
    0.62
     colleague
    0.61
     handkerchief
    0.61
    companion
    0.61
     cousin
    0.61
    Activations Density 0.056%

    No Known Activations