© 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. 84115
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and computations

    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
    ίη
    -1.23
    っちゃった
    -1.16
     pulsera
    -1.16
    齁
    -1.15
    ÑOS
    -1.15
     siglos
    -1.14
    afficheront
    -1.13
     schoenen
    -1.13
     бампер
    -1.13
     kwi
    -1.12
    POSITIVE LOGITS
     will
    1.84
     but
    1.30
    newArrayList
    1.29
    Todavía
    1.28
    >−
    1.27
    院校
    1.19
    También
    1.16
    此
    1.13
    aneity
    1.13
    Aún
    1.12
    Activations Density 0.001%

    No Known Activations