© 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. 34-GEMMASCOPE-RES-131K
    4. 90034
    Prev
    Next
    INDEX
    Explanations

    Mitromorpha ambigua

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

    camera equipment specifications, particularly lens models and their technical details.

    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
     immigration
    -0.74
    feste
    -0.70
     trường
    -0.68
    اقل
    -0.67
    ొ
    -0.66
    тические
    -0.66
     azul
    -0.66
    presets
    -0.66
     Reservation
    -0.65
     attribution
    -0.65
    POSITIVE LOGITS
    kit
    0.92
     kit
    0.90
     aphid
    0.85
    kits
    0.84
    Kit
    0.78
     dám
    0.78
     Typing
    0.77
     Kit
    0.76
    TextSize
    0.75
     Yandex
    0.75
    Activations Density 0.015%

    No Known Activations