© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14063
    Prev
    Next
    INDEX
    Explanations

    craigslist, Objective, Q, In Vivo

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

    The neuron activates on terms referring to online classified‐ad services or classifieds sections (e.g. “craigslist,” “classified,” “Backpage,” “gumtree”).

    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
    薷
    -2.63
    縠
    -2.61
    
    -2.34
     we
    -2.31
     ‘‘
    -2.23
    釤
    -2.11
    freien
    -2.11
    いても
    -2.06
     إجراء
    -2.00
    scriptcase
    -1.98
    POSITIVE LOGITS
    ')
    2.23
    '
    2.16
    と
    2.09
    >
    2.06
    ("
    2.00
    ":
    1.99
    ='
    1.98
    𝕖
    1.95
    ()"
    1.95
     a
    1.94
    Activations Density 0.003%

    No Known Activations