© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36368
    Prev
    Next
    INDEX
    Explanations

    file/package downloading references

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

    The neuron spotlights typical package‐formula metadata fields (like “url,” “version,” “sha256,” “homepage,” etc.) in code or build‐script fragments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Campionato
    -1.25
     fhort
    -1.25
     many
    -1.23
     reafon
    -1.23
    Приятного
    -1.21
     new
    -1.19
     bereits
    -1.13
    продам
    -1.12
    IDENCE
    -1.11
    $\%$
    -1.10
    POSITIVE LOGITS
     заявил
    1.21
     Алексей
    1.16
    ша
    1.15
     però
    1.14
     долла
    1.13
     canh
    1.13
     ita
    1.12
    makeConstraints
    1.12
     mực
    1.11
    mazan
    1.09
    Activations Density 0.045%

    No Known Activations