© 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. 10-GEMMASCOPE-RES-131K
    7. 127900
    Prev
    Next
    INDEX
    Explanations

    Endemic fauna or species

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

    category tags and taxonomic classifications at the beginnings of lines.

    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_10/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
     resistente
    -1.20
    arakhand
    -1.20
     compacto
    -1.18
     esmeralda
    -1.16
     responsibly
    -1.16
    雠
    -1.13
    elasticsearch
    -1.07
    时代的
    -1.06
     mention
    -1.04
    ！！！”
    -1.02
    POSITIVE LOGITS
     già
    1.38
     cuando
    1.30
     quando
    1.22
    udere
    1.16
     poignée
    1.13
    обзор
    1.11
    ać
    1.09
     when
    1.08
     فقط
    1.07
     obiettivo
    1.05
    Activations Density 0.196%

    No Known Activations