© 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. 76102
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptors

    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
     all
    -0.94
     not
    -0.92
     ALL
    -0.86
     taking
    -0.86
     any
    -0.86
    Lịch
    -0.84
     creating
    -0.82
     from
    -0.80
     our
    -0.79
     F
    -0.78
    POSITIVE LOGITS
     magnificent
    1.09
     masterful
    1.03
     majestic
    1.03
    perhaps
    1.02
     horrid
    1.01
    NOTAS
    1.01
     スリーブ
    0.99
     mediocre
    0.98
     astounding
    0.98
     deliciously
    0.98
    Activations Density 0.003%

    No Known Activations