© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 74985
    Prev
    Next
    INDEX
    Explanations

    explaining 'how' and 'about'

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

    This neuron primarily detects the section‐title token “About” (as used in headers or navigation labels).

    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
     and
    -1.66
    ).
    -1.48
     also
    -1.43
    ="
    -1.25
     среда
    -1.24
     them
    -1.22
    also
    -1.21
    
    -1.19
    ):
    -1.19
    "]:
    -1.17
    POSITIVE LOGITS
    ducers
    1.90
    criminate
    1.58
     its
    1.48
    estimable
    1.47
    つた
    1.45
    什么时候
    1.42
     oferece
    1.40
     about
    1.39
     necessary
    1.38
    我还是
    1.38
    Activations Density 0.022%

    No Known Activations