© 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. 129125
    Prev
    Next
    INDEX
    Explanations

    evidence for

    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
     accumulation
    -0.06
    etrot
    -0.06
     몇
    -0.06
     چند
    -0.06
     ಪ್ರದೇಶ
    -0.05
     unwittingly
    -0.05
    Accum
    -0.05
     kilku
    -0.05
    accumulation
    -0.05
     činjen
    -0.05
    POSITIVE LOGITS
    最初は
    0.07
     Evidence
    0.07
    Evidence
    0.07
    Как
    0.07
     аласыз
    0.07
     Excellence
    0.07
    evidence
    0.07
    所以
    0.07
     EVIDENCE
    0.07
     evidence
    0.06
    Activations Density 0.025%

    No Known Activations