© 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. 22-GEMMASCOPE-RES-131K
    7. 65997
    Prev
    Next
    INDEX
    Explanations

    reporting scientific findings

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

    citations in academic papers with author names followed by parenthetical references.

    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_22/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
     "`
    -1.15
    ariats
    -1.13
    izó
    -1.08
    της
    -1.08
    летия
    -1.07
    ADY
    -1.07
     lanzó
    -1.05
     *}
    -1.03
    țiile
    -1.03
     nuovi
    -1.03
    POSITIVE LOGITS
     siècles
    1.19
     update
    1.12
     report
    1.09
     mostaza
    1.08
     studies
    1.07
     gdzie
    1.02
     suggests
    1.01
     îles
    1.01
     enfermo
    1.00
     aceites
    1.00
    Activations Density 0.023%

    No Known Activations