© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78555
    Prev
    Next
    INDEX
    Explanations

    self-storage and medical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    references to storage units, facilities, and self-storage services.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Seating
    -0.80
     fluor
    -0.74
    iliano
    -0.74
    Offsets
    -0.72
     apic
    -0.72
    }~
    -0.71
    blacklist
    -0.71
    irte
    -0.71
     Seats
    -0.70
     Reset
    -0.70
    POSITIVE LOGITS
     storage
    2.39
     Storage
    2.25
    Storage
    2.02
    storage
    1.88
    STORAGE
    1.83
     STORAGE
    1.60
    getStorage
    1.55
     storing
    1.49
     facility
    1.43
    orage
    1.38
    Activations Density 0.019%

    No Known Activations