© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91845
    Prev
    Next
    INDEX
    Explanations

    scanning followed by microscopy type

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

    terms related to scanning microscopy techniques used in scientific research.

    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
     EARLY
    -0.78
     cycles
    -0.77
    Ἀ
    -0.77
    early
    -0.76
     Cycles
    -0.75
    preserved
    -0.75
    iesis
    -0.74
     Garland
    -0.73
     Cycle
    -0.73
     promesas
    -0.73
    POSITIVE LOGITS
     cơm
    0.69
    쥐
    0.66
    unjuk
    0.64
    鵰
    0.60
     резер
    0.60
    셸
    0.60
    ượu
    0.60
     handheld
    0.59
    婢
    0.59
     reef
    0.59
    Activations Density 0.076%

    No Known Activations