© 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. 9481
    Prev
    Next
    INDEX
    Explanations

    action verbs and prepositions

    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
     they
    -1.09
     tény
    -1.07
    atuan
    -1.02
     confirmado
    -0.96
     tentativo
    -0.93
     between
    -0.93
     capturar
    -0.92
     further
    -0.92
    obrá
    -0.92
    They
    -0.91
    POSITIVE LOGITS
     this
    1.91
     überhaupt
    1.70
     böyle
    1.32
     इत
    1.22
    如此
    1.20
     solch
    1.18
     столь
    1.16
     هذا
    1.14
     these
    1.08
     vůbec
    1.04
    Activations Density 0.041%

    No Known Activations