© 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. 32285
    Prev
    Next
    INDEX
    Explanations

    entrance to something

    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
    开头
    -1.01
    냑
    -0.94
    does
    -0.94
    すっ
    -0.93
     окон
    -0.89
    TokenNameDOT
    -0.88
    门口
    -0.85
    Initial
    -0.85
    started
    -0.84
     какого
    -0.84
    POSITIVE LOGITS
     into
    1.16
     from
    1.01
    处的
    1.00
    sbereich
    1.00
     thereto
    0.98
     fee
    0.96
     via
    0.95
    way
    0.92
     with
    0.92
     сюда
    0.91
    Activations Density 0.012%

    No Known Activations