© 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. 2351
    Prev
    Next
    INDEX
    Explanations

    more of, for, than, like

    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
    basically
    -1.48
    somewhat
    -1.47
    absolutely
    -1.47
    ܆
    -1.43
    extremely
    -1.43
     extremely
    -1.37
    albeit
    -1.37
     plafon
    -1.36
    essentially
    -1.36
    饸
    -1.29
    POSITIVE LOGITS
     of
    2.80
     than
    2.33
     like
    2.23
     along
    1.65
     on
    1.52
     Like
    1.47
     akin
    1.46
     towards
    1.37
     suited
    1.36
     Along
    1.34
    Activations Density 0.021%

    No Known Activations