© 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. 49806
    Prev
    Next
    INDEX
    Explanations

    months in 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_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
     that
    -1.10
     or
    -1.07
     или
    -1.06
    宴会
    -1.02
     mengikut
    -1.00
    seiko
    -0.99
     أو
    -0.99
    renia
    -0.96
    After
    -0.95
     but
    -0.94
    POSITIVE LOGITS
    accessed
    1.08
    Accessed
    0.99
    gefügt
    0.98
    慫
    0.95
    瞠
    0.94
     différentes
    0.92
     mehrm
    0.91
     accessed
    0.91
     когато
    0.91
     разных
    0.90
    Activations Density 0.011%

    No Known Activations