© 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. 498
    Prev
    Next
    INDEX
    Explanations

    Impact of

    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
     illuminating
    -1.17
    The
    -1.06
     inim
    -1.02
     appealing
    -1.01
    中最
    -0.98
     самой
    -0.98
     "'
    -0.97
     グリーン
    -0.96
     earnestly
    -0.95
    THERE
    -0.95
    POSITIVE LOGITS
    Impact
    1.69
     Impact
    1.62
     on
    1.59
     impact
    1.22
    impact
    1.20
     craters
    1.18
     assessment
    1.15
    グルト
    1.10
    ful
    1.08
    滙
    1.06
    Activations Density 0.022%

    No Known Activations