© 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
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3742
    Prev
    Next
    INDEX
    Explanations

    splitting strings from lines

    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
    Term
    1.28
    yh
    1.20
    Þ
    1.17
    jde
    1.17
     incurring
    1.14
     termos
    1.13
    Telephone
    1.08
    小小
    1.08
    =$
    1.07
     마치
    1.06
    POSITIVE LOGITS
    ริญ
    1.42
     defaultdict
    1.24
    haltens
    1.15
    脈
    1.12
    рб
    1.11
    اج
    1.11
     Dominican
    1.11
    pherd
    1.10
     unst
    1.08
    чення
    1.08
    Activations Density 0.052%

    No Known Activations