© 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. 10-GEMMASCOPE-RES-131K
    7. 10360
    Prev
    Next
    INDEX
    Explanations

    in addition or also

    np_acts-logits-general · gemini-2.5-flash-lite

    The main thing this neuron does is find numeric expressions (especially multi‐digit numbers and decimal values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     there
    -1.49
     she
    -1.33
    izarse
    -1.26
     lumina
    -1.25
     pomocí
    -1.24
    givings
    -1.22
     alum
    -1.21
     olmayan
    -1.20
     représentants
    -1.19
     Tidak
    -1.18
    POSITIVE LOGITS
     to
    1.87
     also
    1.77
     також
    1.54
     Also
    1.53
     också
    1.48
     επίσης
    1.48
    </td>
    1.45
    also
    1.45
     cũng
    1.44
     également
    1.41
    Activations Density 0.493%

    No Known Activations