© 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. 50356
    Prev
    Next
    INDEX
    Explanations

    a followed by a state or situation

    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
    шет
    -0.93
     bypassing
    -0.91
    ンの
    -0.89
    FOO
    -0.85
    一面
    -0.85
     ludicrous
    -0.84
     twists
    -0.83
    berserk
    -0.81
    lässlich
    -0.81
     baffling
    -0.80
    POSITIVE LOGITS
    batross
    0.96
     learning
    0.94
     exercise
    0.92
     choose
    0.91
     zoo
    0.88
     parlor
    0.88
     guessing
    0.88
     revolving
    0.88
    buyers
    0.88
     circus
    0.87
    Activations Density 0.054%

    No Known Activations