© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 12407
    Prev
    Next
    INDEX
    Explanations

    months and urls

    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_13_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
     tingkat
    1.63
     건강
    1.60
     업체
    1.55
     mendatang
    1.55
     ikut
    1.54
     zwró
    1.52
     fasilitas
    1.51
    傗
    1.48
     rencana
    1.48
     유지
    1.47
    POSITIVE LOGITS
     of
    1.61
     and
    1.36
    of
    1.28
     и
    1.16
    cc
    1.08
    sof
    1.07
    ometrical
    1.00
    omed
    1.00
    (!)
    0.98
    lex
    0.97
    Activations Density 0.066%

    No Known Activations