© 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. 112388
    Prev
    Next
    INDEX
    Explanations

    happiness and the concepts around it

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

    The neuron activates on occurrences of “happy” or “happiness,” i.e. explicit mentions of that state.

    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
    lgica
    -1.99
     usual
    -1.89
    änemark
    -1.88
    versaire
    -1.84
     ";
    -1.81
    '))
    -1.65
    usual
    -1.65
    ীয়
    -1.63
     '
    -1.63
     včetně
    -1.62
    POSITIVE LOGITS
    .
    2.00
    Also
    1.95
    4
    1.82
    在此
    1.68
    }
    1.63
    ]
    1.63
    就像
    1.59
     circumstance
    1.49
    <b>
    1.47
    「
    1.46
    Activations Density 0.014%

    No Known Activations