© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95530
    Prev
    Next
    INDEX
    Explanations

    academic journal titles

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

    the names or abbreviations of academic journals in reference citations.

    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
     other
    -1.36
     costi
    -1.24
     your
    -1.23
     that
    -1.20
     positiven
    -1.20
     compone
    -1.16
     processi
    -1.15
     legislat
    -1.15
     any
    -1.14
     stazione
    -1.13
    POSITIVE LOGITS
    ,
    1.10
    вода
    1.08
     récemment
    1.02
    ӥ
    1.01
    -
    0.99
     Гри
    0.99
    БЕ
    0.98
    thanh
    0.98
    暧
    0.97
    БИ
    0.97
    Activations Density 0.011%

    No Known Activations