© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32967
    Prev
    Next
    INDEX
    Explanations

    past events and actions

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

    the introduction of attributed statements or sources in news reporting, e.g. reporting verbs like “says”/“said” and source identifiers such as “police,” “officials,” or “workers.”

    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
     in
    -1.14
    Leírás
    -1.13
     and
    -1.05
     can
    -1.02
    tabIndex
    -0.96
     as
    -0.94
    咂
    -0.94
    ˮ
    -0.92
    ánt
    -0.92
     különböz
    -0.92
    POSITIVE LOGITS
     после
    1.34
     לאחר
    1.30
     ابتدا
    1.29
     після
    1.20
     initially
    1.12
     was
    1.05
     afterwards
    1.03
     originally
    1.01
    Setelah
    1.00
     بعد
    0.99
    Activations Density 0.076%

    No Known Activations