© 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. 35144
    Prev
    Next
    INDEX
    Explanations

    ASCII, Two, Air, Q, ( symbols

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

    This neuron detects blocks of repeated characters, as found in ASCII‐art or similar repeated‐letter sequences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     specifically
    -1.61
     explicitly
    -1.49
     inherently
    -1.43
     overtly
    -1.41
     How
    -1.36
     There
    -1.30
     також
    -1.29
     needed
    -1.29
     purposely
    -1.28
     but
    -1.27
    POSITIVE LOGITS
    などを
    1.30
     Gouvernement
    1.26
    <bos>
    1.26
     ////
    1.23
     faciliter
    1.22
     Parlement
    1.20
     borg
    1.19
    d
    1.17
     LUMI
    1.17
     praktische
    1.16
    Activations Density 0.000%

    No Known Activations