© 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. 82358
    Prev
    Next
    INDEX
    Explanations

    actual, actually

    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
     very
    -1.31
    very
    -1.25
     rất
    -1.21
     labai
    -1.18
     מאוד
    -1.09
     bardzo
    -1.05
     nagyon
    -0.99
     svært
    -0.98
     later
    -0.98
     unbedingt
    -0.96
    POSITIVE LOGITS
     actual
    2.20
     actually
    1.88
     наконец
    1.77
     instead
    1.74
     faktiskt
    1.68
    บ้าง
    1.64
     Actually
    1.63
    actual
    1.62
    Actually
    1.61
    ACTUAL
    1.55
    Activations Density 0.110%

    No Known Activations