© 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. 67419
    Prev
    Next
    INDEX
    Explanations

    advocacy organizations, teams, support

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

    This neuron activates on mentions of “advocacy” or its close variants (e.g., “advocates”).

    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
    ]
    -2.56
    '
    -2.56
     was
    -2.55
     are
    -2.30
     praised
    -2.28
     may
    -2.27
     will
    -2.23
    に
    -2.22
     described
    -2.16
    }
    -2.16
    POSITIVE LOGITS
    ⬮
    2.50
    ...\
    2.41
    Ꮸ
    2.39
    趼
    2.31
     quell
    2.28
    ﭼ
    2.28
     egregious
    2.27
    during
    2.27
    wasn
    2.25
     aksesuar
    2.25
    Activations Density 0.002%

    No Known Activations