© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48377
    Prev
    Next
    INDEX
    Explanations

    embitterment or BIT(n) flags

    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
     fotball
    -0.75
     linseed
    -0.71
     屏
    -0.70
     beruht
    -0.70
     Downloader
    -0.69
    に似
    -0.68
    kates
    -0.68
    バッグ
    -0.68
     supprimer
    -0.66
    βολ
    -0.66
    POSITIVE LOGITS
     bitter
    6.13
    bitter
    4.84
     bitterness
    4.78
     Bitter
    4.72
    Bitter
    4.41
    苦
    3.28
     bitterly
    3.23
     BIT
    3.11
     Bit
    3.00
     bitters
    2.83
    Activations Density 0.046%

    No Known Activations