© 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-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 764
    Prev
    Next
    INDEX
    Explanations

    net

    np_acts-logits-general · gemini-2.5-flash-lite

    helpful punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    と思いますが
    0.58
    かもしれませんが
    0.56
    いますが
    0.49
    다라고
    0.47
     없고
    0.46
    していますが
    0.46
     ****",
    0.45
    きましたが
    0.45
    ませんが
    0.44
    】,
    0.44
    POSITIVE LOGITS
    。
    1.34
    .
    1.22
    ®.
    1.18
    .`
    1.10
    *.
    1.09
    .*
    1.09
    ™.
    1.09
    .。
    1.08
    .<
    1.07
    ."
    1.06
    Activations Density 13.179%

    No Known Activations