© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130665
    Prev
    Next
    INDEX
    Explanations

    October Harry Styles Jimi Hendrix

    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
     hingga
    -0.07
     sehingga
    -0.07
    新的
    -0.07
     neuen
    -0.07
     khiến
    -0.07
     descoper
    -0.07
     nuovi
    -0.06
     alongside
    -0.06
    让你
    -0.06
     новым
    -0.06
    POSITIVE LOGITS
     during
    0.06
    during
    0.05
     =
    0.05
     छठ
    0.05
     amber
    0.05
     they
    0.05
     inadvertently
    0.05
     عین
    0.05
    艶
    0.05
     bah
    0.05
    Activations Density 0.005%

    No Known Activations