© 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. 76699
    Prev
    Next
    INDEX
    Explanations

    readonly access

    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
     lahko
    -0.88
    rikt
    -0.87
    踉
    -0.81
     '../../../../
    -0.81
     '@
    -0.80
     (~(
    -0.79
    pensione
    -0.79
     Estos
    -0.79
    >*/
    -0.78
    alsy
    -0.78
    POSITIVE LOGITS
     ogó
    0.96
     fields
    0.90
    ness
    0.86
    Nemo
    0.80
     prawda
    0.80
    BufferException
    0.79
     teile
    0.77
     außer
    0.76
    写的
    0.75
    locks
    0.73
    Activations Density 0.023%

    No Known Activations