© 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. 81615
    Prev
    Next
    INDEX
    Explanations

    voracious appetite, reading novels

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

    The neuron fires on descriptive modifiers—especially adjectives and adverbs conveying strong or vivid qualities.

    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
    }$}
    -0.82
    贸易
    -0.81
    Artifact
    -0.80
     experimento
    -0.79
     cristal
    -0.79
    )();
    -0.79
    getHeight
    -0.78
     exports
    -0.77
     பா
    -0.76
     covalent
    -0.76
    POSITIVE LOGITS
     vor
    3.50
     insatiable
    2.97
     raven
    2.75
     hungry
    2.42
     devouring
    2.36
     greedy
    2.34
     devour
    2.33
    Vor
    2.31
    vor
    2.27
     avid
    2.25
    Activations Density 0.080%

    No Known Activations