© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31726
    Prev
    Next
    INDEX
    Explanations

    defining terms after collectively

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Founded
    -0.81
    lore
    -0.79
    Rolf
    -0.76
    そうですが
    -0.75
     only
    -0.75
     with
    -0.75
    न्दु
    -0.74
     Established
    -0.74
     Lora
    -0.74
     根据
    -0.72
    POSITIVE LOGITS
     referred
    4.03
    referred
    3.09
     termed
    2.45
     refer
    2.44
    Refer
    2.36
     known
    2.08
     refers
    1.97
     collectively
    1.95
     okreś
    1.94
     refere
    1.90
    Activations Density 0.213%

    No Known Activations