© 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. 73905
    Prev
    Next
    INDEX
    Explanations

    future development or progression

    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
     praktischen
    -1.06
    つも
    -0.98
     embalaje
    -0.98
     BaseModel
    -0.98
    ggings
    -0.96
    unsqueeze
    -0.96
    伤口
    -0.95
    榉
    -0.95
     hés
    -0.94
     actualizada
    -0.94
    POSITIVE LOGITS
     later
    3.05
     subsequently
    1.95
     eventually
    1.91
     subsequent
    1.74
     future
    1.71
    后来
    1.71
    later
    1.68
     further
    1.68
     other
    1.66
     später
    1.65
    Activations Density 0.070%

    No Known Activations