© 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. 130282
    Prev
    Next
    INDEX
    Explanations

    things liked or chosen

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

    The neuron spikes on occurrences of the word “prefer,” marking expressions of personal preference.

    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
    ꔹ
    -2.73
    ᠊
    -2.58
     Ausdrücke
    -2.52
    푣
    -2.41
     на
    -2.38
     keberadaan
    -2.31
     \
    -2.28
     occurrences
    -2.23
    𖤍
    -2.20
    </b>
    -2.19
    POSITIVE LOGITS
    媜
    2.55
    0
    2.36
     raiſ
    2.36
    
    2.31
     дів
    2.31
     ,‬
    2.23
    including
    2.22
    </h3>
    2.22
    寕
    2.19
     zoude
    2.16
    Activations Density 0.007%

    No Known Activations