© 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. 13448
    Prev
    Next
    INDEX
    Explanations

    verification and credibility of reports

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

    The neuron flags terms and phrases used when questioning, verifying, or calling into doubt the authenticity or origins of a claim.

    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
     pensando
    -1.02
    家は
    -1.02
     uygun
    -1.00
    ﻣ
    -0.96
    batsman
    -0.92
    регистри
    -0.89
    したのは
    -0.88
     criticise
    -0.85
     anuncios
    -0.85
    afterEach
    -0.84
    POSITIVE LOGITS
     verification
    1.84
     verified
    1.60
     подтвер
    1.54
     verifying
    1.49
     credibility
    1.47
     verify
    1.46
     Verification
    1.40
     confirmation
    1.38
     проверить
    1.36
     reliability
    1.33
    Activations Density 0.070%

    No Known Activations