© 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. 34-GEMMASCOPE-RES-131K
    7. 109568
    Prev
    Next
    INDEX
    Explanations

    townland and parish

    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_34/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
     Grade
    -0.74
     Pg
    -0.66
     beziehen
    -0.66
    Dere
    -0.66
     Inspire
    -0.65
    igslist
    -0.65
    aptors
    -0.65
     التي
    -0.65
     gekenn
    -0.64
    のコ
    -0.64
    POSITIVE LOGITS
     parish
    0.94
     [:
    0.77
    ">[
    0.71
    øst
    0.70
     fandom
    0.69
    plaats
    0.69
    Herbert
    0.68
    Proverbs
    0.68
     espèce
    0.66
    ässe
    0.66
    Activations Density 0.033%

    No Known Activations