© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128545
    Prev
    Next
    INDEX
    Explanations

    redirecting users or content

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

    The neuron fires on occurrences of “redirect” (and its inflected forms like “redirecting,” “redirection,” etc.).

    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
     we
    -2.64
    ↵↵
    -2.58
    o
    -2.42
    -
    -2.34
     t
    -2.27
     But
    -2.25
     la
    -2.23
    di
    -2.13
     me
    -2.06
     le
    -2.02
    POSITIVE LOGITS
    縯
    2.81
    
    2.66
     起毛
    2.66
     nowa
    2.50
    摃
    2.42
    ୌ
    2.42
    尨
    2.33
     eſſ
    2.33
    𐀀
    2.30
    礽
    2.23
    Activations Density 0.007%

    No Known Activations