© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59573
    Prev
    Next
    INDEX
    Explanations

    entrance hall or entryway

    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
     murale
    -0.79
    ljiv
    -0.76
    łod
    -0.74
     menyerang
    -0.71
     anlaş
    -0.71
    fenster
    -0.71
    vans
    -0.71
    頜
    -0.71
     cláus
    -0.71
     окна
    -0.71
    POSITIVE LOGITS
     entry
    3.16
     foyer
    3.09
     Entry
    2.72
    Entry
    2.67
     entrance
    2.52
     lobby
    2.52
    entry
    2.47
     Entrance
    2.11
    ENTRY
    2.06
     ENTRY
    1.99
    Activations Density 0.029%

    No Known Activations