© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39224
    Prev
    Next
    INDEX
    Explanations

    despite phrases that contrast

    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_22/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
     includes
    -1.88
     was
    -1.86
     soon
    -1.81
    出了一
    -1.78
    l
    -1.77
    ↵↵
    -1.73
     has
    -1.70
     after
    -1.70
     definitely
    -1.68
    ].
    -1.66
    POSITIVE LOGITS
     the
    2.64
     eenig
    2.20
     parfü
    2.19
    鸱
    2.13
    CHREIB
    2.13
     verhind
    2.13
    錞
    2.09
    屃
    2.08
    鲧
    2.06
    赑
    2.06
    Activations Density 0.013%

    No Known Activations