© 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. 34733
    Prev
    Next
    INDEX
    Explanations

    without further

    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
    more
    -1.20
     também
    -1.16
    again
    -1.08
    another
    -1.02
    latest
    -1.01
    MORE
    -0.99
     Longer
    -0.99
     Fewer
    -0.98
    various
    -0.98
    También
    -0.96
    POSITIVE LOGITS
     further
    1.08
     any
    1.03
     additional
    0.94
     future
    0.94
     svůj
    0.78
    っぷり
    0.78
    president
    0.75
     anymore
    0.75
    缺點
    0.73
     Verhältnis
    0.73
    Activations Density 0.046%

    No Known Activations