© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13602
    Prev
    Next
    INDEX
    Explanations

    stuff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    μφ
    2.48
    atak
    2.42
    া
    2.38
    edian
    2.31
     dibuat
    2.19
    anın
    2.18
    a
    2.17
    uchten
    2.15
    ۰۰
    2.15
    atı
    2.11
    POSITIVE LOGITS
    ුරු
    2.86
    𝓸
    2.67
     speak
    2.60
    𝐲
    2.57
    urricular
    2.57
    siye
    2.54
    urization
    2.51
    瘍
    2.50
     spoke
    2.45
    ាន់
    2.44
    Activations Density 0.008%

    No Known Activations