© 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. 10-GEMMASCOPE-RES-131K
    4. 29102
    Prev
    Next
    INDEX
    Explanations

    two worlds together

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron primarily activates on mentions of “world” or “worlds” (and closely related terms like “realms”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     as
    -2.30
     a
    -1.80
     but
    -1.60
     Pristupljeno
    -1.44
     and
    -1.42
     in
    -1.38
     during
    -1.32
     an
    -1.31
     time
    -1.30
    .”
    -1.30
    POSITIVE LOGITS
     другие
    1.59
     hybride
    1.56
     parfois
    1.49
     mixta
    1.41
     éstos
    1.41
     recupera
    1.41
     eki
    1.38
     چیه
    1.36
     facilita
    1.34
     charmant
    1.34
    Activations Density 0.041%

    No Known Activations