© 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. 10-GEMMASCOPE-RES-131K
    7. 111217
    Prev
    Next
    INDEX
    Explanations

    introduces followed by colon or preposition

    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_10/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
     it
    -1.67
     a
    -1.65
     de
    -1.63
     del
    -1.60
    </h4>
    -1.51
    d
    -1.44
    Xc
    -1.39
    Jm
    -1.37
     when
    -1.32
     told
    -1.32
    POSITIVE LOGITS
    Ultimately
    1.97
    Rather
    1.91
    Instead
    1.86
    Interestingly
    1.84
    Still
    1.83
    What
    1.80
    If
    1.78
    Nonetheless
    1.78
    Additionally
    1.78
    Those
    1.77
    Activations Density 0.000%

    No Known Activations