© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 131051
    Prev
    Next
    INDEX
    Explanations

    measurement and analysis terms

    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_10/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
    嘿嘿
    -2.81
    在他
    -2.77
    在我
    -2.70
    }
    -2.67
    j
    -2.53
    a
    -2.47
    her
    -2.30
     необходи
    -2.25
     thee
    -2.22
     exalted
    -2.20
    POSITIVE LOGITS
    They
    2.75
    </strong>
    2.63
    縷
    2.58
     Hinblick
    2.56
     Betracht
    2.44
     neuem
    2.39
    ~!
    2.36
    ”:
    2.34
    </h3>
    2.33
    喈
    2.31
    Activations Density 0.016%

    No Known Activations