© 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. 53821
    Prev
    Next
    INDEX
    Explanations

    construct validity, tumor induction

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

    non-English text characters, particularly Asian languages.

    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
    文件的
    -0.85
     só
    -0.81
    VertexBuffer
    -0.78
    userType
    -0.78
     unaweza
    -0.77
     Lam
    -0.76
    גל
    -0.76
     informally
    -0.75
    越來越
    -0.74
     resiliency
    -0.74
    POSITIVE LOGITS
     member
    0.93
    nowu
    0.91
     zmniejs
    0.91
    Member
    0.88
    member
    0.88
     Member
    0.85
    MEMBER
    0.83
    り返
    0.82
     ressort
    0.82
     produzione
    0.81
    Activations Density 0.004%

    No Known Activations