© 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. 67947
    Prev
    Next
    INDEX
    Explanations

    the followed by a specific noun

    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
     영화
    -1.14
     Humanos
    -1.10
     GARANT
    -1.09
     lehetős
    -1.08
    Spesifikasi
    -1.07
    Manfaat
    -1.05
     TÉCNICA
    -1.05
     которые
    -1.04
     MÉXICO
    -1.04
    zapatillas
    -1.02
    POSITIVE LOGITS
     specified
    1.63
     chosen
    1.61
     given
    1.49
     selected
    1.40
     that
    1.30
     designated
    1.29
     desired
    1.29
     particular
    1.24
     previously
    1.18
     its
    1.15
    Activations Density 0.085%

    No Known Activations