© 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. 84418
    Prev
    Next
    INDEX
    Explanations

    good followed by names

    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
    ందు
    -0.88
     男の子
    -0.80
     geeft
    -0.79
     thingy
    -0.76
    pado
    -0.75
     cognition
    -0.74
     divest
    -0.72
    labelledby
    -0.71
     chocs
    -0.70
    割と
    -0.70
    POSITIVE LOGITS
    good
    1.17
    Good
    1.16
     Good
    1.02
     good
    0.99
    有好
    0.87
     dobr
    0.83
     GOOD
    0.82
    日時
    0.80
    嗖
    0.80
     Desde
    0.79
    Activations Density 0.032%

    No Known Activations