© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60315
    Prev
    Next
    INDEX
    Explanations

    came out automatically

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

    The neuron fires on verbs or verb compounds that include an “out” directional element (e.g. “shoot out,” “squeezed out,” Chinese “出了,” “出现,” etc.).

    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
            
    -2.77
    man
    -2.48
     or
    -2.23
    ization
    -2.20
    }$
    -2.09
     эту
    -2.08
    um
    -2.03
    鏖
    -2.02
    even
    -1.98
    ;
    -1.96
    POSITIVE LOGITS
    苾
    2.41
    神
    2.36
     regard
    2.28
    彀
    2.27
     放題
    2.19
     Infir
    2.16
    ﮕ
    2.14
    夲
    2.14
    椚
    2.13
     gewisse
    2.08
    Activations Density 0.001%

    No Known Activations