© 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. 129636
    Prev
    Next
    INDEX
    Explanations

    Saccharomyces cerevisiae

    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
    相关
    -0.07
     connexes
    -0.06
     relevant
    -0.06
     அது
    -0.06
    相關
    -0.06
     également
    -0.06
    ້ອຍ
    -0.06
     hochwert
    -0.06
     bueno
    -0.06
     relacionado
    -0.06
    POSITIVE LOGITS
    늙
    0.06
    ).
    0.06
     clan
    0.06
    sport
    0.05
    damage
    0.05
     जोख
    0.05
    emotion
    0.05
    ))).
    0.05
    久し
    0.05
     Global
    0.05
    Activations Density 0.006%

    No Known Activations