© 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. 118820
    Prev
    Next
    INDEX
    Explanations

    number per each

    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
     counting
    -0.07
     follow
    -0.06
     strong
    -0.06
    μεν
    -0.06
     seulement
    -0.06
    ése
    -0.06
     Gegen
    -0.06
     beri
    -0.06
    ގެ
    -0.06
     strengthening
    -0.06
    POSITIVE LOGITS
     each
    0.10
     mỗi
    0.08
    each
    0.08
     каждом
    0.07
    แต่ละ
    0.07
     każdy
    0.07
     প্রতিটি
    0.07
     каждый
    0.07
     fiecare
    0.07
    Each
    0.06
    Activations Density 0.069%

    No Known Activations