© 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. 22-GEMMASCOPE-RES-131K
    7. 92905
    Prev
    Next
    INDEX
    Explanations

    Many commercially, Download logo, Nitric

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

    The neuron fires on long continuous sequences of uppercase hexadecimal digits (0–9, A–F).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    にします
    -1.09
     wspania
    -1.08
     jaka
    -1.07
    nti
    -1.03
     Lesen
    -1.01
     immense
    -1.01
    すっ
    -1.00
    わけです
    -0.99
     vélos
    -0.99
     oczy
    -0.98
    POSITIVE LOGITS
     only
    1.16
     probably
    1.09
     surprisingly
    1.09
     mostly
    1.06
     not
    1.02
     actually
    1.01
    ｾ
    1.01
     still
    1.00
    作詞
    0.99
     Surprisingly
    0.99
    Activations Density 0.001%

    No Known Activations