© 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. 75112
    Prev
    Next
    INDEX
    Explanations

    modelmodel package import entity class

    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
    知道的
    -1.10
    会在
    -1.09
    UTIVE
    -1.09
    蜮
    -1.08
    }
    -1.08
     avaient
    -1.02
     beide
    -1.01
    ਗ਼
    -1.01
    ⽼
    -0.98
    owulf
    -0.97
    POSITIVE LOGITS
    斫
    1.21
    You
    1.16
    壟
    1.11
    ۠
    1.11
     Anhang
    1.10
     cemetery
    1.10
    ICOLON
    1.09
    ﱠ
    1.09
    It
    1.08
    نکته
    1.08
    Activations Density 0.057%

    No Known Activations