© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117118
    Prev
    Next
    INDEX
    Explanations

    introduction and to promote

    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
    Certain
    -0.07
     scheint
    -0.07
     ended
    -0.06
     offenbar
    -0.06
     ciertos
    -0.06
     indefin
    -0.06
     आखिरकार
    -0.06
    Continued
    -0.06
     certain
    -0.06
     bestimmte
    -0.06
    POSITIVE LOGITS
    odenum
    0.06
     Video
    0.06
    铑
    0.06
    द्रोह
    0.06
     ordinal
    0.05
    Video
    0.05
     baddies
    0.05
     minor
    0.05
     второго
    0.05
    ,
    0.05
    Activations Density 0.005%

    No Known Activations