© 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. 116290
    Prev
    Next
    INDEX
    Explanations

    tight ass, balls deep

    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
     Lufthansa
    -0.07
     및
    -0.06
    मुंबई
    -0.06
     termasuk
    -0.06
     Focused
    -0.06
    🔦
    -0.06
     спец
    -0.06
    🏩
    -0.06
     pada
    -0.06
     Cups
    -0.06
    POSITIVE LOGITS
     borough
    0.06
     penetration
    0.06
     theyre
    0.06
    난다
    0.06
     interchangeably
    0.05
     youre
    0.05
    bardziej
    0.05
     deploying
    0.05
     harassment
    0.05
     стрель
    0.05
    Activations Density 0.006%

    No Known Activations