© 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. 13-GEMMASCOPE-2-RES-16K
    7. 2155
    Prev
    Next
    INDEX
    Explanations

    squash thighs sharding slaves sphynx prater

    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
    ి
    2.53
    alnız
    2.50
    ીએ
    2.47
    ੀ
    2.35
     {{\
    2.33
    ي
    2.31
     Yönet
    2.29
     Rxa
    2.29
    ⿹
    2.27
    anın
    2.26
    POSITIVE LOGITS
    theless
    3.02
    withstanding
    2.98
    xiety
    2.84
    обходимо
    2.66
    spapers
    2.50
    ногда
    2.47
    hibition
    2.38
    ductory
    2.32
    noon
    2.30
    etheless
    2.30
    Activations Density 1.499%

    No Known Activations