© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130741
    Prev
    Next
    INDEX
    Explanations

    SPDX-License-Identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scammers
    -0.06
     ONLY
    -0.06
     ficam
    -0.06
    ONLY
    -0.06
    ほとんど
    -0.05
     szó
    -0.05
    generator
    -0.05
     angene
    -0.05
     use
    -0.05
     ય
    -0.05
    POSITIVE LOGITS
     stwor
    0.08
     создать
    0.07
    creating
    0.07
    establishing
    0.06
    ప్తి
    0.06
     by
    0.06
     особое
    0.06
     skapa
    0.06
     வாங்க
    0.06
    签订
    0.06
    Activations Density 0.001%

    No Known Activations