© 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. 8943
    Prev
    Next
    INDEX
    Explanations

    Rift, riffs, Rift Valley, Rift Zone, Rift Previews

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

    The neuron responds to occurrences of the letter sequence “rif” (as in “riff,” “riffing,” or “rift”) in words.

    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
    灕
    -2.63
     этом
    -2.59
     одном
    -2.58
    閙
    -2.58
     namn
    -2.53
    疍
    -2.50
    
    -2.42
    慙
    -2.41
    
    -2.38
    馐
    -2.36
    POSITIVE LOGITS
    '
    2.33
    "
    2.16
     But
    2.14
    ’
    2.09
    harapkan
    2.05
    чал
    2.03
     "
    2.02
    名叫
    1.95
    巨大的
    1.93
    pasang
    1.93
    Activations Density 0.003%

    No Known Activations