© 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. 45607
    Prev
    Next
    INDEX
    Explanations

    Pod followed by specific words

    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
     fehlt
    -0.77
     Kv
    -0.69
    ŀ
    -0.69
     klingt
    -0.69
     Persi
    -0.68
     звука
    -0.67
    琊
    -0.67
     rơi
    -0.66
    ected
    -0.66
     صدای
    -0.66
    POSITIVE LOGITS
     pod
    1.05
    Pod
    0.97
     Pod
    0.93
    خصوص
    0.82
     demás
    0.81
    pod
    0.79
     pods
    0.77
     شک
    0.77
    POD
    0.75
     répondre
    0.74
    Activations Density 0.017%

    No Known Activations