© 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. 22-GEMMASCOPE-RES-131K
    7. 27394
    Prev
    Next
    INDEX
    Explanations

    descriptions of trips and places

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

    The neuron flags high-content “keyword” tokens—i.e. the semantically important nouns, verbs, and adjectives that carry the main topic of 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_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
     problems
    -1.51
     cérami
    -1.42
     portatil
    -1.39
     things
    -1.36
     berle
    -1.25
    stuffs
    -1.20
     summari
    -1.18
     niega
    -1.16
    Formerly
    -1.16
     Technologien
    -1.16
    POSITIVE LOGITS
     you
    1.38
    SafeMath
    1.31
    ﻻ
    1.30
    ﻷ
    1.25
     витами
    1.20
     fön
    1.20
     Covid
    1.20
     your
    1.19
    пит
    1.19
    хів
    1.16
    Activations Density 0.017%

    No Known Activations