© 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. 66311
    Prev
    Next
    INDEX
    Explanations

    timestamps and dates

    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
    ritus
    -1.00
     matt
    -0.92
    好不好
    -0.90
    所有人
    -0.89
    תוך
    -0.89
     героя
    -0.88
     menina
    -0.87
     Kette
    -0.85
    ticulate
    -0.84
     detto
    -0.83
    POSITIVE LOGITS
     time
    1.06
    unique
    1.03
     July
    0.96
    vaila
    0.94
    Referenties
    0.89
    interval
    0.88
    vancing
    0.84
    linspace
    0.84
     range
    0.82
    └──
    0.82
    Activations Density 0.029%

    No Known Activations