© 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. 34-GEMMASCOPE-RES-131K
    7. 84665
    Prev
    Next
    INDEX
    Explanations

    [1] [2] [0]

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

    The neuron fires on bracketed reference markers (e.g. “[1]”, “[808]”) used for citations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     from
    -1.00
     almost
    -0.98
     Hidup
    -0.90
     Khusus
    -0.85
    øb
    -0.85
    )}.
    -0.85
    方才
    -0.85
    subpackage
    -0.84
    Almost
    -0.82
    '};
    -0.81
    POSITIVE LOGITS
    </tr>
    0.95
    ]
    0.94
    НОЙ
    0.90
    )
    0.90
     😊
    0.90
     reservados
    0.86
     utiliser
    0.85
     verbund
    0.84
    应当
    0.84
     legales
    0.84
    Activations Density 0.001%

    No Known Activations