© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84698
    Prev
    Next
    INDEX
    Explanations

    describing models and problems

    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
     ascertaining
    -0.89
     зависит
    -0.87
    pies
    -0.83
    fireEvent
    -0.81
    QUANT
    -0.81
     सुन
    -0.77
     method
    -0.76
    PROCEDURE
    -0.76
    和其他
    -0.75
    debe
    -0.75
    POSITIVE LOGITS
     studied
    1.41
     with
    1.35
     where
    1.22
     arise
    1.18
     discussed
    1.12
     arises
    1.02
     encountered
    1.00
     treated
    1.00
     relevant
    0.98
     přip
    0.96
    Activations Density 0.115%

    No Known Activations