© 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. 116921
    Prev
    Next
    INDEX
    Explanations

    set intersection

    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
    ओवर
    -0.06
     eşit
    -0.06
     tambien
    -0.06
     ils
    -0.06
    localPosition
    -0.06
     Elektrokhimiya
    -0.06
     이를
    -0.06
     automaticamente
    -0.06
     cualquiera
    -0.06
    ✬
    -0.05
    POSITIVE LOGITS
     पहिल्या
    0.07
     mainly
    0.07
    مص
    0.06
     Md
    0.06
     अलावा
    0.06
     علاوہ
    0.06
    ከት
    0.06
     énon
    0.06
     glavni
    0.06
     початку
    0.06
    Activations Density 0.001%

    No Known Activations