© 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. 81391
    Prev
    Next
    INDEX
    Explanations

    downstream effectors

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

    terms related to downstream molecular or mechanical effects in scientific literature.

    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
    Aspiration
    -0.75
    zeichnis
    -0.75
    filesize
    -0.75
    miro
    -0.73
    资产
    -0.73
     intuitive
    -0.72
    ancey
    -0.72
     aprove
    -0.69
    psfrag
    -0.69
    Progressive
    -0.69
    POSITIVE LOGITS
     effector
    3.53
     Eff
    2.50
    eff
    2.48
    Eff
    2.31
     effect
    1.79
     effec
    1.71
     EFFECT
    1.70
    效应
    1.55
     Effect
    1.48
     eff
    1.48
    Activations Density 0.184%

    No Known Activations