© 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. 25949
    Prev
    Next
    INDEX
    Explanations

    grammatical question or correction

    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
    ロナ
    -0.75
     accompan
    -0.74
     strangle
    -0.72
     bàn
    -0.70
    กุ
    -0.70
    オク
    -0.69
     perplex
    -0.69
     pretensions
    -0.68
     originator
    -0.68
    Assist
    -0.67
    POSITIVE LOGITS
     repetition
    1.81
    iteration
    1.52
     rhetorical
    1.21
     devices
    1.15
     repetitive
    1.13
     literary
    1.09
     DEVICES
    1.08
     Devices
    1.05
     repeated
    1.04
     повто
    1.03
    Activations Density 0.017%

    No Known Activations