© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11018
    Prev
    Next
    INDEX
    Explanations

    word fragments and suffixes

    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
    こんな
    1.72
    私が
    1.71
    чних
    1.70
    мона
    1.69
     streamlines
    1.65
     degeneracy
    1.64
    的时
    1.64
    𝐦
    1.63
     каким
    1.63
    ᴍ
    1.62
    POSITIVE LOGITS
    beeld
    1.42
    led
    1.41
    ƙ
    1.36
    headed
    1.25
    backed
    1.20
     Lokal
    1.15
    êt
    1.13
    full
    1.12
    erd
    1.12
     hard
    1.11
    Activations Density 0.000%

    No Known Activations