© 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. 133
    Prev
    Next
    INDEX
    Explanations

    title and name followed by "said"

    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
     Nosotros
    -1.13
     habitaciones
    -1.09
    quatre
    -1.09
     Gebet
    -1.09
    reviewed
    -1.07
    archiviato
    -1.05
    cobacterium
    -1.05
    ercises
    -1.04
    osoba
    -1.03
     eigentlich
    -1.02
    POSITIVE LOGITS
     said
    2.06
     also
    2.03
     added
    1.45
     then
    1.44
     further
    1.34
     urged
    1.22
     furthermore
    1.21
     aumentare
    1.18
     explained
    1.16
     alfo
    1.15
    Activations Density 0.008%

    No Known Activations