© 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. 6762
    Prev
    Next
    INDEX
    Explanations

    of which

    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
    МУ
    -0.94
    对此
    -0.86
     Verfahrens
    -0.82
     svou
    -0.81
     اینکه
    -0.81
    ELIN
    -0.81
    RunAsync
    -0.79
     svůj
    -0.79
     Henrietta
    -0.79
     SPY
    -0.78
    POSITIVE LOGITS
     Gebrauch
    1.05
     beware
    0.98
     make
    0.97
     برخ
    0.95
     uży
    0.95
     made
    0.95
     speaks
    0.92
     بهره
    0.89
    Beware
    0.86
     αποτε
    0.85
    Activations Density 0.012%

    No Known Activations