© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14653
    Prev
    Next
    INDEX
    Explanations

    Tyson, PTI, industry, heterosexual couples

    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
    }
    -3.14
     utilize
    -2.53
     induce
    -2.34
     multitude
    -2.34
     produce
    -2.31
     inflict
    -2.25
    轳
    -2.25
     imply
    -2.25
     behöver
    -2.23
     encourage
    -2.22
    POSITIVE LOGITS
    .
    2.89
     apparaat
    2.69
     животные
    2.44
    想要的
    2.42
    耵
    2.39
     ausein
    2.33
    蟶
    2.31
     gearbeitet
    2.30
    地圖
    2.28
     zustand
    2.28
    Activations Density 0.007%

    No Known Activations