© 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. 1095
    Prev
    Next
    INDEX
    Explanations

    absolute value expressions

    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
     ?$
    -1.70
    klinik
    -1.59
     riche
    -1.55
     tkan
    -1.51
     salari
    -1.50
     sabias
    -1.50
    罍
    -1.49
     intrig
    -1.48
    ———-
    -1.45
     Če
    -1.44
    POSITIVE LOGITS
    7
    2.20
    8
    2.09
    3
    2.06
    6
    1.93
    2
    1.93
    4
    1.82
    </strong>
    1.80
    '
    1.80
     -
    1.78
    9
    1.76
    Activations Density 0.009%

    No Known Activations