© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1271
    Prev
    Next
    INDEX
    Explanations

    word completions

    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
    hoo
    0.63
    HLER
    0.63
     tur
    0.61
     Tur
    0.60
     ane
    0.58
     hoo
    0.57
     Hin
    0.56
    풋
    0.56
    Tur
    0.55
    Talk
    0.55
    POSITIVE LOGITS
     diferenciales
    0.65
     intermediaries
    0.62
    नीत
    0.62
    কীর
    0.61
    卡
    0.61
     intermedi
    0.60
     фо
    0.59
     rekening
    0.59
    amol
    0.59
    ീസ്
    0.58
    Activations Density 0.267%

    No Known Activations