© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7428
    Prev
    Next
    INDEX
    Explanations

    approximations, inherent, variations, empowerment, assumed

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

    The neuron selectively fires on subword pieces that begin longer, content-bearing words (i.e. word‐root prefixes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }
    0.35
    {
    0.33
    ]
    0.31
    ں
    0.30
    )
    0.29
    \
    0.29
    >
    0.29
    !
    0.29
    %
    0.29
    '}
    0.29
    POSITIVE LOGITS
    த்தகைய
    0.32
     उपकरणों
    0.30
     reimag
    0.30
     использу
    0.30
     análise
    0.29
     буквально
    0.29
    로운
    0.28
    롭게
    0.28
     пользова
    0.28
    ளுக்கான
    0.28
    Activations Density 0.129%

    No Known Activations