© 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. 76275
    Prev
    Next
    INDEX
    Explanations

    mixed deciduous woodlands

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

    natural or geographic features in text, particularly related to woodlands, forests, and natural environments.

    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
     desierto
    -0.88
    ofus
    -0.84
    žen
    -0.80
    鉢
    -0.80
     PRES
    -0.80
     terras
    -0.77
    Sector
    -0.77
    orado
    -0.77
    ştir
    -0.77
    らい
    -0.76
    POSITIVE LOGITS
     hed
    2.84
     hedge
    2.36
     hedges
    2.14
     Hed
    1.58
    Hed
    1.56
     hedging
    1.51
    hedge
    1.48
     Hedge
    1.47
    hed
    1.38
     Hedges
    1.21
    Activations Density 0.034%

    No Known Activations