© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104445
    Prev
    Next
    INDEX
    Explanations

    structured data keys

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

    property names or keys in structured data formats like JSON, JavaScript objects, and code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     xvi
    -1.07
     pulsante
    -1.02
    あまり
    -1.01
     trygg
    -1.00
     vermittelt
    -1.00
     mse
    -0.99
     }.
    -0.98
     authentic
    -0.98
     tratti
    -0.98
    yczny
    -0.97
    POSITIVE LOGITS
     mercado
    1.25
     también
    1.20
    Máy
    1.15
     Existenz
    1.14
    Resin
    1.13
    xffffffff
    1.13
     rejet
    1.13
     motivadoras
    1.13
     esthétique
    1.13
    痂
    1.12
    Activations Density 0.044%

    No Known Activations