© 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. 128578
    Prev
    Next
    INDEX
    Explanations

    of the same

    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
     benzer
    -0.07
     similar
    -0.06
    人生
    -0.06
    本质
    -0.06
     изд
    -0.06
     vardır
    -0.06
    elben
    -0.06
     distinct
    -0.06
     monotonicity
    -0.06
    彼此
    -0.06
    POSITIVE LOGITS
     유형
    0.07
     тип
    0.07
     அதை
    0.06
    加坡
    0.06
     å
    0.06
    tipo
    0.06
     pierws
    0.06
     implicate
    0.05
     крупные
    0.05
     उस
    0.05
    Activations Density 0.010%

    No Known Activations