© 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. 22-GEMMASCOPE-RES-131K
    4. 39520
    Prev
    Next
    INDEX
    Explanations

    plans and proposals being discussed

    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_22/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
     frambo
    -1.41
     spion
    -1.38
    Puntos
    -1.38
    kész
    -1.37
     territoriale
    -1.36
     اپنے
    -1.35
    PUESTA
    -1.34
     visse
    -1.34
     دخترانه
    -1.32
     tenda
    -1.32
    POSITIVE LOGITS
     plans
    1.63
     project
    1.60
     plan
    1.54
     options
    1.52
     proposals
    1.41
     feasibility
    1.36
     funds
    1.34
     proposal
    1.34
     плани
    1.31
     investors
    1.30
    Activations Density 0.098%

    No Known Activations