© 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. 98422
    Prev
    Next
    INDEX
    Explanations

    regular intervals

    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
     продолжает
    -1.28
    ்ச
    -1.16
    οντας
    -1.13
    jskiej
    -1.09
    appliquent
    -1.09
    тные
    -1.08
     хочет
    -1.06
     část
    -1.02
    kmale
    -0.98
    砝
    -0.98
    POSITIVE LOGITS
     annually
    1.46
     you
    1.35
     year
    1.35
     annual
    1.19
    magini
    1.15
    ikkert
    1.14
    prakti
    1.13
     вам
    1.13
     yearly
    1.13
     your
    1.11
    Activations Density 0.019%

    No Known Activations