© 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. 109362
    Prev
    Next
    INDEX
    Explanations

    rotary pump, multiplicity tree, glucose metabolism

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

    programming code or technical content, particularly focusing on parentheses, brackets, and specialized technical terminology.

    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
    今天
    -0.86
    අ
    -0.83
    বং
    -0.82
     Tori
    -0.81
     Beli
    -0.80
    letch
    -0.80
    respectively
    -0.80
    čky
    -0.79
     MU
    -0.77
    GAL
    -0.77
    POSITIVE LOGITS
    goto
    1.13
     IL
    1.03
     goto
    0.92
    il
    0.90
     goes
    0.88
    brtc
    0.79
    IL
    0.79
     отмеча
    0.79
     excluding
    0.77
     überprüft
    0.77
    Activations Density 0.000%

    No Known Activations