© 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. 12994
    Prev
    Next
    INDEX
    Explanations

    questions starting with "What is" or related to "Q:"

    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
    auces
    -1.31
     like
    -1.27
     információk
    -1.23
    lentes
    -1.23
     really
    -1.16
     Vorschlag
    -1.16
     esportivo
    -1.12
     cadeiras
    -1.12
     bebê
    -1.09
     everyone
    -1.09
    POSITIVE LOGITS
    钥
    1.41
    Ṇ
    1.32
    וּ
    1.32
    ּוֹ
    1.26
     бампер
    1.24
    ͙
    1.23
     umumnya
    1.17
     Hinsicht
    1.16
     sommige
    1.15
    uck
    1.14
    Activations Density 0.003%

    No Known Activations