© 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. 39626
    Prev
    Next
    INDEX
    Explanations

    match citations or specific punctuation

    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
     profesion
    -1.28
     Automó
    -1.26
     krav
    -1.25
     sond
    -1.23
     of
    -1.23
     turist
    -1.20
     guir
    -1.18
     textil
    -1.17
     péro
    -1.16
    UMENTO
    -1.16
    POSITIVE LOGITS
     is
    1.17
    niña
    1.08
    doi
    1.07
     mutfak
    1.01
    eddable
    1.00
     encontrada
    0.99
    Antenna
    0.99
     nepiecieš
    0.99
    initas
    0.98
     zvuky
    0.96
    Activations Density 0.002%

    No Known Activations