© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66986
    Prev
    Next
    INDEX
    Explanations

    ensure not happening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     understand
    -1.45
    Transk
    -1.34
     know
    -1.34
    最后由
    -1.32
     would
    -1.29
     properly
    -1.24
    ﷽
    -1.24
     mantend
    -1.21
    <?
    -1.20
     navigu
    -1.20
    POSITIVE LOGITS
    optarg
    1.20
    「
    1.16
    ГУ
    1.16
    ６
    1.15
    voer
    1.13
    ４
    1.13
     превра
    1.08
    使用
    1.08
     أشهر
    1.08
    maxn
    1.06
    Activations Density 0.026%

    No Known Activations