© 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. 22-GEMMASCOPE-RES-131K
    7. 67877
    Prev
    Next
    INDEX
    Explanations

    class instance identifier

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

    The neuron activates on occurrences of the word “instance” (as in instance variables or class instances).

    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
    雱
    -2.48
    甞
    -2.42
    }$
    -2.41
    廕
    -2.34
     работают
    -2.27
     但
    -2.25
     ワイド
    -2.23
     unſ
    -2.17
    蛲
    -2.17
    莇
    -2.14
    POSITIVE LOGITS
     для
    2.66
     For
    2.53
    al
    2.44
     Then
    2.42
     για
    2.38
    ஂ
    2.34
     untuk
    2.31
     für
    2.27
     FOR
    2.27
     leur
    2.23
    Activations Density 0.018%

    No Known Activations