© 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. 117075
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     অভিন
    -0.06
     ранее
    -0.06
    給
    -0.06
    就是
    -0.06
    previously
    -0.06
    ":
    -0.05
     aiutare
    -0.05
     среди
    -0.05
     كتابه
    -0.05
     няко
    -0.05
    POSITIVE LOGITS
     and
    0.07
    ปลาย
    0.06
     scheming
    0.06
     WHICH
    0.06
     قریب
    0.06
     buzzing
    0.06
     holde
    0.06
    ीट
    0.06
     reverber
    0.06
     medieval
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.