© 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. 11726
    Prev
    Next
    INDEX
    Explanations

    helping explain concepts

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

    This neuron fires on infrequent or unusual vocabulary items—i.e. rare tokens.

    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
    ático
    0.75
    }$-(
    0.75
    }|\
    0.74
    embeddings
    0.72
    }(
    0.71
    }({\
    0.70
    вная
    0.69
     prothorax
    0.69
    ये
    0.68
    cter
    0.68
    POSITIVE LOGITS
     VON
    0.80
     seism
    0.75
     denaro
    0.75
     cread
    0.73
     hjälp
    0.73
     що
    0.71
     Що
    0.70
     журнала
    0.68
     ‎
    0.68
     、,
    0.68
    Activations Density 0.000%

    No Known Activations