© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2445
    Prev
    Next
    INDEX
    Explanations

    Last Modified By

    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
    сни
    0.65
    स
    0.62
    सं
    0.62
    ْس
    0.61
    س
    0.61
    sete
    0.59
    સ્પ
    0.59
    𝒔
    0.59
    щини
    0.58
    SIM
    0.57
    POSITIVE LOGITS
    бой
    0.79
    bae
    0.64
    bok
    0.64
    бую
    0.60
    beck
    0.60
     bio
    0.60
     Abi
    0.59
    bio
    0.59
     weighting
    0.58
     driv
    0.58
    Activations Density 0.239%

    No Known Activations