© 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. 67623
    Prev
    Next
    INDEX
    Explanations

    introducing descriptive details

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

    The neuron activates specifically on occurrences of the word “featuring.”

    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
    на
    -2.64
     یا
    -2.45
    😻
    -2.36
     fråga
    -2.30
    家の
    -2.14
    ólica
    -2.08
    💜
    -2.08
    larda
    -2.05
    🌸
    -2.02
    💞
    -2.02
    POSITIVE LOGITS
    烀
    2.56
    跸
    2.38
    当下
    2.34
     generando
    2.30
     them
    2.23
     dilapidated
    2.22
     the
    2.20
    
    2.19
     They
    2.16
     hapless
    2.16
    Activations Density 0.004%

    No Known Activations