© 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. 34-GEMMASCOPE-RES-131K
    7. 33525
    Prev
    Next
    INDEX
    Explanations

    out of

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

    The neuron fires strongly on the word “out” (especially when used in “out of” or hyphenated “out-of” constructions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ppich
    -0.70
    にて
    -0.69
     Creep
    -0.68
    abha
    -0.68
    长老
    -0.68
     другим
    -0.68
     Neutr
    -0.66
    iente
    -0.66
     Все
    -0.65
    Citrus
    -0.65
    POSITIVE LOGITS
     OUT
    1.27
     Out
    1.15
    getOut
    1.11
    Door
    1.06
    performs
    1.05
     loud
    1.03
     Door
    1.02
    DOOR
    1.01
    STANDING
    1.01
    Out
    0.98
    Activations Density 0.021%

    No Known Activations