© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13994
    Prev
    Next
    INDEX
    Explanations

    pronouns and location words

    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
     this
    -1.52
    茛
    -1.20
     поэтому
    -1.05
     pembentukan
    -1.00
     därför
    -0.99
     इससे
    -0.97
    })-
    -0.97
    хіво
    -0.96
    なんですよ
    -0.96
     because
    -0.95
    POSITIVE LOGITS
     they
    1.66
    ,
    1.54
     you
    1.27
    Trying
    1.21
     she
    1.15
    男朋友
    1.10
     zamiast
    1.08
    They
    1.06
     we
    1.05
    Notae
    1.05
    Activations Density 0.038%

    No Known Activations