© 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. 34-GEMMASCOPE-RES-131K
    7. 83808
    Prev
    Next
    INDEX
    Explanations

    summoning magic

    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_34/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
     secteur
    -0.79
    Vå
    -0.76
    inigte
    -0.73
     mensagem
    -0.72
    Krie
    -0.71
     Probes
    -0.70
    Romans
    -0.70
     ubicada
    -0.70
    меется
    -0.69
     sacerdote
    -0.68
    POSITIVE LOGITS
     summoning
    1.12
     Solomon
    1.12
    召唤
    0.88
     BIND
    0.87
     summon
    0.86
    Summon
    0.86
    ziek
    0.85
    召喚
    0.85
    Solomon
    0.84
     Summon
    0.83
    Activations Density 0.008%

    No Known Activations