© 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. 90822
    Prev
    Next
    INDEX
    Explanations

    420

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

    The neuron responds to words ending in “-friendly” (e.g. “friendly”).

    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
     the
    -2.61
    跸
    -2.16
     aveva
    -2.08
     avait
    -2.00
    釤
    -2.00
     alcune
    -1.92
     molte
    -1.90
     Then
    -1.89
    ations
    -1.88
    
    -1.85
    POSITIVE LOGITS
    沨
    2.44
    One
    2.19
    With
    2.09
     羅
    2.08
    From
    2.06
    Before
    2.03
    Although
    2.00
    otriva
    1.98
     encourages
    1.96
    When
    1.95
    Activations Density 0.013%

    No Known Activations