© 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. 81677
    Prev
    Next
    INDEX
    Explanations

    shipwrecks and strandings

    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
    WEBSITE
    -0.85
     plunging
    -0.82
    Organizer
    -0.74
     extermination
    -0.70
     dipping
    -0.68
    ܘ
    -0.68
    Whoo
    -0.67
     Molo
    -0.67
    insane
    -0.67
    Website
    -0.66
    POSITIVE LOGITS
     stranded
    2.09
     strand
    1.71
     bea
    1.68
    stranded
    1.65
     beach
    1.61
     grounding
    1.60
     échou
    1.58
     grounded
    1.52
     ashore
    1.51
     str
    1.34
    Activations Density 0.031%

    No Known Activations