© 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. 10-GEMMASCOPE-RES-131K
    7. 65038
    Prev
    Next
    INDEX
    Explanations

    printers, printability, Rinpoche, Sugden, citations

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

    The neuron fires on the four‐letter character sequence “prin” (in any word containing “prin”), i.e. it detects the substring “prin.”

    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
    ation
    -3.13
    e
    -3.11
    in
    -2.81
     techniczne
    -2.66
     ด้วย
    -2.63
    isation
    -2.63
    на
    -2.56
    }
    -2.47
     minis
    -2.45
     exquisite
    -2.44
    POSITIVE LOGITS
    亖
    3.36
    鬭
    3.31
    栳
    3.30
    𞤤
    3.23
    鼇
    3.20
    錸
    3.20
    舠
    3.19
     ſame
    3.13
    鈇
    3.05
    錞
    3.03
    Activations Density 0.008%

    No Known Activations