© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2251
    Prev
    Next
    INDEX
    Explanations

    sentence ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    她在
    2.40
     (’
    2.26
     ʼ
    2.21
     (‘
    2.13
     DataTable
    2.11
    —“
    2.11
    ⼤
    2.07
     nombreux
    2.06
    鈥
    2.06
    sbom
    2.05
    POSITIVE LOGITS
    rinsic
    3.17
     nhé
    2.86
    7
    2.77
    6
    2.64
     anyways
    2.57
    8
    2.38
    trimenti
    2.38
    5
    2.35
    3
    2.34
     ;)
    2.31
    Activations Density 2.542%

    No Known Activations