© 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. 15383
    Prev
    Next
    INDEX
    Explanations

    scientific and technical topics

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

    code snippets with XML or programming language syntax.

    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
     hunde
    -1.34
     its
    -1.32
     siang
    -1.29
     kym
    -1.25
    lijken
    -1.24
     onsdag
    -1.23
     keramik
    -1.22
     vek
    -1.17
     this
    -1.16
     from
    -1.15
    POSITIVE LOGITS
     and
    1.24
     invece
    1.12
     titan
    1.07
    informe
    1.05
    מעות
    1.05
    きち
    1.05
     principalement
    1.04
     takich
    1.03
    是啊
    1.03
    Ami
    1.02
    Activations Density 0.000%

    No Known Activations