© 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. 49846
    Prev
    Next
    INDEX
    Explanations

    startup business and incubation

    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
    水的
    -0.87
    ffichage
    -0.86
    UNES
    -0.85
     Hinsicht
    -0.85
     apó
    -0.83
     catholique
    -0.82
     delantero
    -0.82
    算是
    -0.81
    tactos
    -0.79
     stings
    -0.79
    POSITIVE LOGITS
     incubator
    1.33
     incubation
    1.16
     incub
    1.08
     Incub
    0.98
     accelerator
    0.98
     founders
    0.98
     incubated
    0.97
     companionship
    0.93
     padx
    0.85
    Weekend
    0.84
    Activations Density 0.012%

    No Known Activations