© 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. 91135
    Prev
    Next
    INDEX
    Explanations

    fort, fortress, castle

    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
     podrob
    -0.82
     žiad
    -0.81
     speedometer
    -0.81
    irvana
    -0.77
    を描
    -0.76
    iksa
    -0.76
    flächen
    -0.75
     Beneath
    -0.75
     evita
    -0.74
    ägen
    -0.74
    POSITIVE LOGITS
     fort
    2.78
     fortress
    2.59
     fortified
    2.48
    fort
    2.13
     castle
    2.05
    Fort
    2.02
     stron
    1.98
     forts
    1.98
     stronghold
    1.96
     Fort
    1.91
    Activations Density 0.043%

    No Known Activations