© 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. 75392
    Prev
    Next
    INDEX
    Explanations

    encounter with people or things

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

    The neuron specifically detects occurrences of the word “encounter” (in any casing).

    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
    as
    -2.94
    N
    -2.83
    TemporalType
    -2.56
    C
    -2.47
    }$
    -2.47
    our
    -2.23
     חבר
    -2.22
    D
    -2.22
    S
    -2.19
     осуществляется
    -2.16
    POSITIVE LOGITS
     ONLY
    2.59
    儅
    2.34
    但他
    2.31
    与此同时
    2.27
    霂
    2.25
    哢
    2.22
    题材
    2.14
    这让
    2.14
    ➢
    2.13
     Beſ
    2.11
    Activations Density 0.008%

    No Known Activations