© 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. 60299
    Prev
    Next
    INDEX
    Explanations

    titles and phrases

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

    The neuron fires on uppercase identifier‐style tokens (e.g. code constants and permission names with underscores).

    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
     by
    -1.36
     all
    -1.13
     in
    -1.05
     with
    -1.04
     as
    -1.02
     on
    -1.00
    ＋
    -1.00
     ALL
    -0.98
     an
    -0.96
     their
    -0.95
    POSITIVE LOGITS
    </td>
    1.45
    Flashcards
    1.16
    bonjour
    1.13
    Goed
    1.11
    Mosa
    1.08
     チュ
    1.02
    Kino
    1.02
    Hiding
    1.00
    HISTOR
    1.00
    Contribu
    0.99
    Activations Density 0.000%

    No Known Activations