© 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
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 4112
    Prev
    Next
    INDEX
    Explanations

    Hungarian place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     prophyl
    1.26
    髪
    1.26
    ン
    1.23
     lysine
    1.22
     taches
    1.21
     thinning
    1.21
    κι
    1.19
     Державний
    1.19
     pir
    1.17
    ノ
    1.17
    POSITIVE LOGITS
    ribusiness
    1.43
    assara
    1.38
    かります
    1.37
    stå
    1.29
    えない
    1.23
    섰
    1.23
    venue
    1.19
    aland
    1.17
    statusCode
    1.17
    줍
    1.16
    Activations Density 0.050%

    No Known Activations