© 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. 119873
    Prev
    Next
    INDEX
    Explanations

    Swift/Objective-C/Java annotations and keywords

    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
    Winner
    -0.07
     luôn
    -0.07
     sorgen
    -0.07
     всегда
    -0.07
     winner
    -0.06
    琲
    -0.06
     statunitense
    -0.06
    自殺
    -0.06
     siempre
    -0.06
     altijd
    -0.06
    POSITIVE LOGITS
     ...,
    0.07
    াফ
    0.06
    িগণ
    0.06
     този
    0.05
     vague
    0.05
     neglecting
    0.05
     هذا
    0.05
     అతని
    0.05
     (...
    0.05
    𝘐
    0.05
    Activations Density 0.002%

    No Known Activations