© 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. 128988
    Prev
    Next
    INDEX
    Explanations

    quoted text

    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
     cursory
    -0.07
     Also
    -0.06
     yellowish
    -0.06
     sleepy
    -0.06
     широ
    -0.06
    ૃતિ
    -0.06
     शुर
    -0.05
     only
    -0.05
     ostensibly
    -0.05
     eyebrows
    -0.05
    POSITIVE LOGITS
     ♪
    0.07
    Forgery
    0.06
    Louisiana
    0.06
    hibit
    0.06
     Louisiana
    0.06
    achment
    0.06
    flora
    0.06
     LIVE
    0.06
     FGD
    0.06
     το
    0.06
    Activations Density 0.009%

    No Known Activations