© 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. 128431
    Prev
    Next
    INDEX
    Explanations

    existence and meaning

    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
     preserves
    -0.06
     कोच
    -0.06
     isnt
    -0.06
     diferencia
    -0.06
    消耗
    -0.06
     lineup
    -0.06
    मा
    -0.05
     hardly
    -0.05
     különb
    -0.05
     Anti
    -0.05
    POSITIVE LOGITS
     centralized
    0.06
     unsecured
    0.06
    íticas
    0.06
     Masse
    0.06
     providence
    0.06
     Cabo
    0.06
    otom
    0.06
     पायल
    0.06
    thai
    0.06
     zonder
    0.06
    Activations Density 0.009%

    No Known Activations