© 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. 119164
    Prev
    Next
    INDEX
    Explanations

    my mum

    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
     prawie
    -0.06
    瑋
    -0.06
     जवळपास
    -0.06
    지에
    -0.06
     enga
    -0.06
     enferm
    -0.06
    收集
    -0.06
    кера
    -0.06
     flott
    -0.06
     rotator
    -0.06
    POSITIVE LOGITS
     برخی
    0.07
    Funny
    0.07
    雖
    0.06
     their
    0.06
     these
    0.06
    onto
    0.06
     Funny
    0.06
     though
    0.06
    虽
    0.06
     now
    0.06
    Activations Density 0.005%

    No Known Activations