© 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
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 4348
    Prev
    Next
    INDEX
    Explanations

    connecting clauses with and but yet

    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
     данный
    1.64
    하였습니다
    1.58
     이용하여
    1.52
     pertanto
    1.51
    .';
    1.49
    또한
    1.47
     somit
    1.46
     successivamente
    1.45
     данного
    1.41
     attualmente
    1.32
    POSITIVE LOGITS
    啧
    2.34
    ちゃう
    2.33
    撂
    2.19
     cringe
    2.13
     heft
    2.10
    嗐
    2.09
     damned
    2.06
     And
    2.05
    甭
    2.03
    わけで
    2.02
    Activations Density 0.492%

    No Known Activations