© 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. 131046
    Prev
    Next
    INDEX
    Explanations

    Tilemachos Chytiris

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    mathrm
    -1.13
    klád
    -1.08
    𝛽
    -1.05
     mollus
    -1.02
    вил
    -0.96
    ⚡️
    -0.93
    ଶ
    -0.90
    を中心に
    -0.90
    gara
    -0.89
     now
    -0.88
    POSITIVE LOGITS
     senhor
    1.16
    alignSelf
    1.07
     sogar
    1.05
     desejo
    1.05
     years
    1.01
    ůměr
    1.00
     each
    1.00
    Zutaten
    0.98
     reacciones
    0.96
     ensuing
    0.96
    Activations Density 0.006%

    No Known Activations