© 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. 76316
    Prev
    Next
    INDEX
    Explanations

    names ending in "am" or "ham"

    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
    ㌔
    -0.95
    rieren
    -0.75
    labelControl
    -0.73
    Mojo
    -0.71
     nightlife
    -0.70
    chtigkeit
    -0.70
    łaści
    -0.68
    雳
    -0.67
     practition
    -0.67
     MOVIE
    -0.67
    POSITIVE LOGITS
    ream
    1.29
    øm
    1.21
    vm
    1.16
     Pham
    1.15
    wasm
    1.15
    xlim
    1.14
    gham
    1.14
    rm
    1.13
    beam
    1.13
    ham
    1.12
    Activations Density 0.080%

    No Known Activations