© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86477
    Prev
    Next
    INDEX
    Explanations

    RFC and NCC documents

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

    The neuron primarily detects standalone capitalized names (proper nouns) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    }
    -3.41
    猡
    -2.78
    毳
    -2.61
    \
    -2.36
     wichtigste
    -2.23
    ſſi
    -2.14
    ↵↵
    -2.11
    瑨
    -2.11
    ского
    -2.09
     oreille
    -2.06
    POSITIVE LOGITS
    ing
    3.05
    ?”
    2.50
    荩
    2.48
    雰
    2.44
    as
    2.41
    时期
    2.33
     sorta
    2.31
    ﻞ
    2.30
    撩
    2.30
    是他
    2.25
    Activations Density 0.015%

    No Known Activations