© 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. 116694
    Prev
    Next
    INDEX
    Explanations

    programming code 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
    }}-\
    -0.06
     may
    -0.06
     পৃথিব
    -0.05
     kell
    -0.05
    (&:
    -0.05
     ſ
    -0.05
     One
    -0.05
     one
    -0.05
    ecc
    -0.05
     sugest
    -0.05
    POSITIVE LOGITS
    が大
    0.07
     други
    0.07
    另一个
    0.07
     otro
    0.07
    Zeit
    0.06
     역시
    0.06
     же
    0.06
     anderes
    0.06
     другим
    0.06
    取り付け
    0.06
    Activations Density 0.016%

    No Known Activations