© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8069
    Prev
    Next
    INDEX
    Explanations

    statistical deviation

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

    The neuron fires on specialized domain‐specific technical terms and acronyms (e.g. DOA, GA, CRL, “listing,” “severity,” etc.).

    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
    ﯿ
    0.73
    ilyl
    0.72
    ждены
    0.71
    posY
    0.69
    ﻞ
    0.67
     ವಿವಿಧ
    0.66
    PAD
    0.66
    ﻠ
    0.65
    Sampler
    0.65
     এসব
    0.64
    POSITIVE LOGITS
    )
    0.96
    ),
    0.73
    ]
    0.69
    );
    0.67
    }
    0.64
     entraî
    0.63
    \}
    0.62
    〕
    0.61
    /
    0.60
    )，
    0.59
    Activations Density 0.233%

    No Known Activations