© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59012
    Prev
    Next
    INDEX
    Explanations

    states or roles

    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
    ksamkeit
    -1.15
     satisfactor
    -1.12
     conspic
    -1.11
    мова
    -1.10
     severa
    -1.09
    common
    -1.07
    üll
    -1.06
    additional
    -1.05
    warning
    -1.04
     pernic
    -1.03
    POSITIVE LOGITS
     a
    2.70
     also
    1.86
     active
    1.74
     an
    1.74
     involved
    1.71
     known
    1.41
     very
    1.38
     always
    1.23
     especially
    1.13
     involve
    1.09
    Activations Density 0.012%

    No Known Activations