© 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. 91324
    Prev
    Next
    INDEX
    Explanations

    coastal erosion

    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
    RAFT
    -0.88
     waterways
    -0.88
     Descent
    -0.81
    井
    -0.81
    CONV
    -0.76
    DAFTAR
    -0.76
    ulier
    -0.76
     Balkan
    -0.75
    ılacak
    -0.75
    Water
    -0.74
    POSITIVE LOGITS
     beach
    1.90
    beach
    1.44
     Beach
    1.35
     erosion
    1.34
    Beach
    1.30
     beaches
    1.11
     nourishment
    1.10
     shore
    1.09
     armor
    1.05
     пля
    1.05
    Activations Density 0.014%

    No Known Activations